Misc writing toward revisions.
This commit is contained in:
Carl Colglazier
parent
713c9ac4ef
commit
69d757e4d6
@ -1,18 +0,0 @@
|
||||
manuscript:
|
||||
article: acm.qmd
|
||||
code-links:
|
||||
- text: Preprocessing
|
||||
href: code/preprocess.py
|
||||
- text: R code
|
||||
href: code/helpers.R
|
||||
- href: code/survival.R
|
||||
notebooks:
|
||||
- notebook: notebooks/_moved.qmd
|
||||
- notebook: notebooks/arima.qmd
|
||||
environment: renv.lock
|
||||
|
||||
execute:
|
||||
freeze: auto
|
||||
|
||||
|
||||
|
||||
@ -1,14 +0,0 @@
|
||||
project:
|
||||
type: manuscript
|
||||
render:
|
||||
- article.qmd
|
||||
manuscript:
|
||||
article: icwsm.qmd
|
||||
environment: renv.lock
|
||||
execute:
|
||||
echo: false
|
||||
error: false
|
||||
warning: false
|
||||
message: false
|
||||
freeze: auto
|
||||
cache: true
|
||||
21
_quarto.yml
21
_quarto.yml
@ -3,8 +3,8 @@ project:
|
||||
output-dir: "_out"
|
||||
preview:
|
||||
port: 2059
|
||||
host: 0.0.0.0
|
||||
browser: false
|
||||
#host: 0.0.0.0
|
||||
#browser: false
|
||||
watch-inputs: true
|
||||
format:
|
||||
acm-html:
|
||||
@ -16,4 +16,19 @@ format:
|
||||
\usepackage{siunitx}
|
||||
docx: default
|
||||
profile:
|
||||
default: acm
|
||||
default: acm
|
||||
manuscript:
|
||||
article: acm.qmd
|
||||
code-links:
|
||||
- text: Preprocessing
|
||||
href: code/preprocess.py
|
||||
- text: R code
|
||||
href: code/helpers.R
|
||||
- href: code/survival.R
|
||||
notebooks:
|
||||
- notebook: notebooks/_moved.qmd
|
||||
- notebook: notebooks/arima.qmd
|
||||
- notebook: notebooks/revisions.qmd
|
||||
environment: renv.lock
|
||||
execute:
|
||||
freeze: auto
|
||||
|
||||
147
acm.qmd
147
acm.qmd
@ -120,7 +120,7 @@ Although attracting and retaining newcomers is a key challenge for online commun
|
||||
|
||||
Mastodon's decentralized design has long been in tension with the disproportionate popularity of a small set of large, general-topic servers within the system [@ramanChallengesDecentralisedWeb2019a]. Analysing the activity of new accounts that join the network, we find that users who sign up on such servers are less likely to remain active after 91 days. We also find that many users who move accounts tend to gravitate toward smaller, more niche servers over time, suggesting that established users may also find additional utility from such servers.
|
||||
|
||||
In response to these findings, we propose a potential way to create server and tag recommendations on Mastodon. This recommendation system could both help newcomers find servers that match their interests and help established accounts discover "neighborhoods" of related servers.
|
||||
In response to these findings, we propose a potential way to create server and tag recommendations on Mastodon. This recommendation system could both help newcomers find servers that match their interests and help established accounts discover "neighborhoods" of related servers to enable further discovery.
|
||||
|
||||
# Background
|
||||
|
||||
@ -136,7 +136,7 @@ Individual Mastodon servers can have an effect on the end experience of users. F
|
||||
|
||||
## The Mastodon Migrations
|
||||
|
||||
Mastodon saw a surge in interest in 2022 and 2023, particularly after Elon Musk's Twitter acquisition. In particular, four events of interests drove measurable increases in new users to the network: the announcement of the acquisition (April 14, 2022), the closing of the acquisition (October 27, 2022), a day when Twitter suspended a number of prominent journalists (December 15, 2022), and a day when Twitter experienced an outage and started rate limiting accounts (July 1, 2023). Many Twitter accounts announced they were setting up Mastodon accounts and linked their new accounts to their followers, often using tags like #TwitterMigration [@heFlockingMastodonTracking2023] and driving interest in Mastodon in a process @lacavaDriversSocialInfluence2023 found consistent with social influence theory.
|
||||
Mastodon saw a surge in interest in 2022 and 2023, particularly after Elon Musk's Twitter acquisition. In particular, four events of interests drove measurable increases in new users to the network: the announcement of the acquisition (April 14, 2022), the closing of the acquisition (October 27, 2022), a day when Twitter suspended a number of prominent journalists (December 15, 2022), and a day when Twitter experienced an outage and started rate limiting accounts (July 1, 2023). Many Twitter accounts announced they were setting up Mastodon accounts and linked their new accounts to their followers, often using tags like `#TwitterMigration`[@heFlockingMastodonTracking2023] and driving interest in Mastodon in a process @lacavaDriversSocialInfluence2023 found consistent with social influence theory.
|
||||
|
||||
Some media outlets have framed reports on Mastodon [@hooverMastodonBumpNow2023] through what @zulliRethinkingSocialSocial2020 calls the "Killer Hype Cycle", whereby the media finds a new alternative social media platform, declares it a potential killer of some established platform, and later calls it a failure if it does not displace the existing platform. Such framing fails to take systems like the Fediverse seriously for their own merits: completely replacing existing commercial systems is not the only way to measure success, nor does it account for the real value the Fediverse provides for its millions of active users.
|
||||
|
||||
@ -150,23 +150,22 @@ The series of migrations of new users into Mastodon in many ways reflect folk st
|
||||
|
||||
## Recommendation Systems and Collaborative Filtering
|
||||
|
||||
Recommendation systems help people with decision-making processes by suggesting items of likely interest [@ricciRecommenderSystemsHandbook2022]. Many contemporary recommendation systems use collaborative filtering, a technique which produces new recommendations based on the preferences of a collection of similar users [@korenAdvancesCollaborativeFiltering2022]. Such systems can be effective at offering relevant suggestions; however, collaborative systems must also deal with the "cold start" problem, where new users have no data to base recommendations on. The cold start problem has three possible facets: boostrapping new communities, dealing with new items, and handling new users. In each case, limited data on the entity makes it impossible to find similar entities without some way of building a profile. Collaborative filtering often also produces a popularity bias where more items enjoyed by a wide range of users receive more recommendations than more obscure but possibly more relevant items.
|
||||
Recommender systems help people filter information to find resources releveant to some need [@ricciRecommenderSystemsHandbook2022]. The development of these systems as an area of formal study harkens back to information retrieval (e.g. @saltonIntroductionModernInformation1987) and foundational works imagining the role of computing in human decision-making (e.g. @bushWeMayThink1945). Early work on these systems produced more effective ways of filtering and sorting documents in searches such as the probabilistic models that motivated the creation of the okapi (BM25) relevance function [@robertsonProbabilisticRelevanceFramework2009]. Many contemporary recommendation systems use collaborative filtering, a technique which produces new recommendations for items based on the preferences of a collection of similar users [@korenAdvancesCollaborativeFiltering2022].
|
||||
|
||||
Collaborative filtering has the added benefit of producing a matches between both similar users and similar items. That is, a collaborative filtering system can find items similar to each other based on having shared users, but it can also find similar users via shared items.
|
||||
Collaborative filtering systems build on top of a user-item-rating ($U-I-r$) model where there is a set of users who each provide ratings for a set of items. The system then uses the ratings from other users to predict the ratings of a user for an item they have not yet rated and uses these predictions to create a ordered list of the best recommendations for the user's needs [@ekstrandCollaborativeFilteringRecommender2011 pp. 86-87]. Collaborative filtering recommender systems typically produce better results as the number of users and items in the system increases; however, they must must also deal with the "cold start" problem, where limited data makes recommendations unviable [@lamAddressingColdstartProblem2008]. The cold start problem has three possible facets: boostrapping new communities, dealing with new items, and handling new users [@schaferCollaborativeFilteringRecommender2007 pp. 311-312]. In each case, limited data on the entity makes it impossible to find similar entities without some way of building a profile. Further, uncorrected collaborative filtering techniques often also produce a bias where more broadly popular items receive more recommendations than more obscure but possibly more relevant items [@zhuPopularityOpportunityBiasCollaborative2021]. Research on collaborative filtering has also shown that the quality of recommendations can be improved by using a combination of user-based and item-based collaborative filtering [@sarwarItembasedCollaborativeFiltering2001]. <!-- TODO: check this -->
|
||||
|
||||
Serveral approaches to collaborative filtering have become commonplace. Many of these use dimensionality reduction, which compress the space
|
||||
This is particularly useful because the matrix of items and users tends to be extremely sparse, e.g. in a movie recommendor system, most people have not seen most of the movies in the database. Singular value decomposition (SVD) is one such dimension reduction technique which transforms a $m \times n$ matrix $M$ into the form $M = U\SigmaV\subset{T}$.
|
||||
Although all forms of collaborative filtering use some combination of users and items, there are two main approaches to collaborative filtering: memory-based and model-based. Memory-based approaches use the entire user-item matrix to make recommendations, while model-based approaches use a reduced form of the matrix to make recommendations. This is particularly useful because the matrix of items and users tends to be extremely sparse, e.g. in a movie recommendor system, most people have not seen most of the movies in the database. Singular value decomposition (SVD) is one such dimension reduction technique which transforms a $m \times n$ matrix $M$ into the form $M = U \Sigma V^{T}$ [@paterekImprovingRegularizedSingular2007]. SVD is particularly useful for recommendation systems because it can be used to find the latent factors which underlie the user-item matrix and use these factors to make recommendations.
|
||||
|
||||
In the Mastodon context, the cold start problem has two possible facets: there is no information on new servers and there is also no information on new users. New servers are thus likely prone to falling for popularity bias: there is simply more data on larger servers. A common strategy to deal with new users is to ask for some intitial preferences to create an initial workable user profile.
|
||||
While researchers in the recommendation system space often focus on ways to design the system to produce good results mathematically, human-computer interaction researchers also consider various human factors which contribute to the overall system. Crucially, McNee et al. argued “being accurate is not enough”: user-centric evaluations, which consider multiple aspects of the user experience, are necessary to evaluate the full system. HCI researchers have also contributed pioneering recommender systems in practice. For example, GroupLens researchers @resnickGrouplensOpenArchitecture1994 craeted a collaborative filtering systems for Usenet and later produced advancements toward system evalulation and explaination of movie recommendations [@herlockerEvaluatingCollaborativeFiltering2004; @herlockerExplainingCollaborativeFiltering2000]. @cosleySuggestBotUsingIntelligent2007 created a system to match people with tasks on Wikipedia to encourage more editing. This prior work shows that recommender systems can be used to help users find relevant information in a variety of contexts.
|
||||
|
||||
The decentralized web presents unique challenges for recommendation systems. Centralized recommendation systems can collect data from all users and use this data to make recommendations. However, this is less desirable on the decentralized web, where data is spread across many servers and users may not want to share their data with a central authority.
|
||||
|
||||
## Evaluation of Recommendation Systems
|
||||
|
||||
Determining the effectiveness of a recommendation system can be tricky because there are usually multiple factors involved [@zangerleEvaluatingRecommenderSystems2022].
|
||||
Evaluating recommender systems can be tricky because a measure of good performance must take into account various dimensions[@zangerleEvaluatingRecommenderSystems2022]. A measure of accuracy must be paired with a question of “accuracy toward what?” Explainability requires a transparent means of showing the user why a certain item was recommended.
|
||||
|
||||
Creators of recommendation systems often decompose evalution into two parts: system-centric evalution and user-centered evalution.
|
||||
It is often important to both start with an end goal in mind and to keep evaluation integrated throughout the entire process of creating a recommender systems, from conceptualization to optimization. There are several considerations to keep in mind such as the trade-off between optimizing suggestions and the risks of over-fitting. For example, a system designed to create suggestions with the highest propensity that the user will like the recommendations may struggle with a reduced diversity of its suggestions.
|
||||
|
||||
Recommender systems can be evaluated using three board categories of techniques: offline, online, and user studies. Offline evaluation uses pre-collected data and a measure to describe the performance of the system, assuming there is insufficient relevance to the difference in time between when the data was collected and the present moment. Online evaluation uses a deployed, live system, e.g. A/B testing. In this case, the user is often unaware of the experiment. In contrast, user studies involve subjects which are aware they are being studied.
|
||||
|
||||
# Data
|
||||
|
||||
@ -227,6 +226,23 @@ num_account_filt <- load_accounts(filt = TRUE) %>% text_format()
|
||||
|
||||
# Analysis and Results
|
||||
|
||||
```{r}
|
||||
# Calculate how "general" a server is based on the simularity matrix.
|
||||
library(tidyverse)
|
||||
library(igraph)
|
||||
library(arrow)
|
||||
|
||||
sim_servers <- "data/scratch/server_similarity.feather" %>% arrow::read_ipc_file() %>% rename("weight" = "Similarity")
|
||||
#sim_net <- as.network(sim_servers)
|
||||
g <- graph_from_data_frame(sim_servers, directed = FALSE)
|
||||
|
||||
g_strength <- log(sort(strength(g)))
|
||||
normalized_strength <- (g_strength - min(g_strength)) / (max(g_strength) - min(g_strength))
|
||||
|
||||
server_centrality <- enframe(normalized_strength, name="server", value="strength")
|
||||
server_centrality %>% arrow::write_ipc_file("data/scratch/server_centrality.feather")
|
||||
```
|
||||
|
||||
## Survival Model
|
||||
|
||||
*Are accounts on suggested general servers less likely to remain active than accounts on other servers?*
|
||||
@ -245,6 +261,8 @@ source(here("code/survival.R"))
|
||||
plot_km
|
||||
```
|
||||
|
||||
### Kaplan–Meier Estimator
|
||||
|
||||
```{r}
|
||||
#| label: table-coxme
|
||||
library(ehahelper)
|
||||
@ -266,8 +284,6 @@ Using `r text_format(sel_a)` accounts created from May 1 to June 30, 2023, we cr
|
||||
|
||||
[^1]: `r paste(general_servers, collapse=", ")`
|
||||
|
||||
::: {.content-visible unless-profile="icwsm"}
|
||||
|
||||
::: {#tbl-cxme .column-body}
|
||||
```{r}
|
||||
if (knitr::is_latex_output()) {
|
||||
@ -281,6 +297,8 @@ Coefficients for the Cox Proportional Hazard Model with Mixed Effects. The model
|
||||
|
||||
:::
|
||||
|
||||
### Mixed Effects Cox Proportional Hazard Model
|
||||
|
||||
|
||||
We also construct a Mixed Effects Cox Proportional Hazard Model
|
||||
|
||||
@ -299,7 +317,17 @@ where $h(t_{ij})$ is the hazard for account $i$ on server $j$ at time $t$, $h_0(
|
||||
|
||||
We again find that accounts on the largest general instances are less likely to remain active than accounts on other servers, while accounts created on smaller servers are more likely to remain active.
|
||||
|
||||
:::
|
||||
### Logistic Regression
|
||||
|
||||
First, we calculate a continuous measure for the generality of the server based on the item-item similarity between servers. We then use this measure to predict whether an account will remain active after 91 days using a logistic regression model.
|
||||
|
||||
```{r}
|
||||
library(modelsummary)
|
||||
|
||||
modelsummary(logit)
|
||||
```
|
||||
|
||||
The results of this analysis again suggests that the generality of the server is negatively associated with the likelihood that an account will remain active after 91 days.
|
||||
|
||||
## Moved Accounts
|
||||
|
||||
@ -373,6 +401,16 @@ One challenge in building such a system is the decentralized nature of the syste
|
||||
|
||||
We evaluate the system in part using the accounts which moved between servers. Based on their posting history (e.g. hashtags), can the recommendations system predict where they will move to?
|
||||
|
||||
In the Mastodon context, the cold start problem has two possible facets: there is no information on new servers and there is also no information on new users. New servers are thus likely prone to falling for popularity bias: there is simply more data on larger servers. A common strategy to deal with new users is to ask for some intitial preferences to create an initial workable user profile.
|
||||
|
||||
The decentralized web presents unique challenges for recommendation systems. Centralized recommendation systems can collect data from all users and use this data to make recommendations. However, this is less desirable on the decentralized web, where data is spread across many servers and users may not want to share their data with a central authority.
|
||||
|
||||
As my recommender system operates under the assumption that smaller, more topic-focused servers are better, it follows that a diverse set of niche results which only match a few tags are more helpful than a set of results which match a larger and more broad set of tags. The system therefore presents results sorted in a manner which encourages a higher diversity of results.
|
||||
|
||||
One current limitation of my system is that it does not account for the relationship between tags, e.g. “union” and “unions” are essentially the same tag and “furry” and “fursuit” are highly related tags which are in similar areas of embedded space. In future revisions, I hope to account for the relationship between similar tags and pull the top servers from clusters of highly related tags with the top priority going to clusters based on their number of selected tags. This system could be implemented efficiently in O(nt) time given a minimum cluster size of $t$.
|
||||
|
||||
The choice of evaluation criteria follows from the goal or user need to provide relevant, specific, and plausible good servers for a set of tags. We test the relevance of the system based on the posting patterns of users who chose to move from one server to another. Crucially, these users were previously familiar with Mastodon before setting up their next account and, as shown in the previous section, these users tend to move toward smaller, more niche servers. We evaluate the recommender system by measuring the rank k of their destination server. We use the formula...
|
||||
|
||||
|
||||
## Recommendation System Design
|
||||
|
||||
@ -402,22 +440,7 @@ We then used the normalized TF-IDF matrix to produce recommendations using SVD.
|
||||
|
||||
## Applications
|
||||
|
||||
```{r}
|
||||
#| eval: false
|
||||
library(tidyverse)
|
||||
library(igraph)
|
||||
library(arrow)
|
||||
|
||||
sim_servers <- "data/scratch/server_similarity.feather" %>% arrow::read_ipc_file() %>% rename("weight" = "Similarity")
|
||||
#sim_net <- as.network(sim_servers)
|
||||
g <- graph_from_data_frame(sim_servers, directed = FALSE)
|
||||
|
||||
g_strength <- log(sort(strength(g)))
|
||||
normalized_strength <- (g_strength - min(g_strength)) / (max(g_strength) - min(g_strength))
|
||||
|
||||
server_centrality <- enframe(normalized_strength, name="server", value="strength")
|
||||
server_centrality %>% arrow::write_ipc_file("data/scratch/server_centrality.feather")
|
||||
```
|
||||
|
||||
### Server Similarity Neighborhoods
|
||||
|
||||
@ -429,7 +452,7 @@ $$
|
||||
\text{similarity}(A, B) = \frac{A \cdot B}{\|A\| \|B\|}
|
||||
$$
|
||||
|
||||
::: {#tbl-sim-servers .content-visible unless-profile="icwsm"}
|
||||
::: {#tbl-sim-servers}
|
||||
|
||||
```{r}
|
||||
#| label: table-sim-servers
|
||||
@ -458,17 +481,45 @@ Top five servers most similar to hci.social
|
||||
|
||||
:::
|
||||
|
||||
### Server Discovery
|
||||
|
||||
Given a set of popular tags and a list of servers, we build a recommendation system where users select tags from a list of popular tags and receive server suggestions. The system first creates a subset of vectors based on the TF-IDF matrix which represents the top clusters of topics. After a user selects the top tags of interest to them, it suggests servers which match their preferences.
|
||||
|
||||
### Tag Similarity
|
||||
|
||||
We also calculate the similarity between tags using the same method. This can be used to suggest related tags to users based on their interests.
|
||||
|
||||
::: {.content-visible unless-profile="icwsm"}
|
||||
```{r}
|
||||
#| fig-cap: "100 popular hashtags visualized in two dimensions using a principal component analysis (PCA) on the transformed singular value decomposition (SVD) matrix."
|
||||
library(tidyverse)
|
||||
library(arrow)
|
||||
library(ggrepel)
|
||||
library(here)
|
||||
library(jsonlite)
|
||||
|
||||
## Rubustness to Limited Data
|
||||
top_tags <- "data/scratch/tag_svd.feather" %>% arrow::read_ipc_file() %>%
|
||||
as_tibble %>%
|
||||
mutate(s = variance * log(count)) %>% arrange(desc(s))
|
||||
|
||||
top_tags %>%
|
||||
select(tag, index) %>%
|
||||
jsonlite::write_json(here("recommender/data/top_tags.json"))
|
||||
|
||||
top_tags %>%
|
||||
head(100) %>%
|
||||
ggplot(aes(x = x, y = y, label = tag)) +
|
||||
geom_text_repel(size = 2.5, max.overlaps = 20) +
|
||||
#geom_point() +
|
||||
theme_minimal()
|
||||
```
|
||||
|
||||
### Server Discovery
|
||||
|
||||
Given a set of popular tags and a list of servers, we build a recommendation system where users select tags from a list of popular tags and receive server suggestions. The system first creates a subset of vectors based on the TF-IDF matrix which represents the top clusters of topics. After a user selects the top tags of interest to them, it suggests servers which match their preferences.
|
||||
|
||||
## Evaluation
|
||||
|
||||
### Server Recommendations for Users
|
||||
|
||||
For evaluation, we use data from posts on accounts during a different time period from the one we used to train the recommender system. The goal of the system is to suggest the best servers for these accounts.
|
||||
|
||||
### Rubustness to Limited Data
|
||||
|
||||
```{r}
|
||||
#| label: fig-simulations-rbo
|
||||
@ -496,7 +547,6 @@ A challenge for a federated recommendation system like we propose is that it nee
|
||||
|
||||
We simulated various scenarios that limit both servers that report data and the number of tags they report. We used rank biased overlap (RBO) to then compare the outputs from these simulations to the baseline with more complete information from all tags on all servers [@webberSimilarityMeasureIndefinite2010]. In particular, we gave a higher weight to suggestions with a higher rank, with weights decaying by a factor of $k^{0.80}$. @fig-simulations-rbo shows how the average agreement with the baseline scales, which take the top 256 tags from each server.
|
||||
|
||||
:::
|
||||
|
||||
# Discussion
|
||||
|
||||
@ -504,6 +554,8 @@ The analysis can also be improved by additionally focusing on factors lead to ac
|
||||
|
||||
The observational nature of the data limit some of the causal claims we can make. It is unclear, for instance, if accounts on general servers are less likely to remain active because of the server itself or because of the type of users who join such servers. For example, it is conceivable that the kind of person who spends more time researching which server to join is more invested in their Mastodon experience than one who simply joins the first server they find.
|
||||
|
||||
|
||||
|
||||
## Future Work
|
||||
|
||||
Future work is necessary to determine the how well the recommendation system is at helping users find servers that match their interests. This may involve user studies and interviews to determine how well the system works in practice.
|
||||
@ -534,29 +586,6 @@ library(ggrepel)
|
||||
theme_minimal()
|
||||
```
|
||||
|
||||
```{r}
|
||||
library(tidyverse)
|
||||
library(arrow)
|
||||
library(ggrepel)
|
||||
library(here)
|
||||
library(jsonlite)
|
||||
|
||||
top_tags <- "data/scratch/tag_svd.feather" %>% arrow::read_ipc_file() %>%
|
||||
as_tibble %>%
|
||||
mutate(s = variance * log(count)) %>% arrange(desc(s))
|
||||
|
||||
top_tags %>%
|
||||
select(tag, index) %>%
|
||||
jsonlite::write_json(here("recommender/data/top_tags.json"))
|
||||
|
||||
top_tags %>%
|
||||
head(100) %>%
|
||||
ggplot(aes(x = x, y = y, label = tag)) +
|
||||
geom_text_repel(size = 3, max.overlaps = 10) +
|
||||
#geom_point() +
|
||||
theme_minimal()
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
## Glossary {.appendix}
|
||||
|
||||
@ -52,11 +52,15 @@ general_servers <- c(
|
||||
"ohai.social"
|
||||
) # > 100 cohort size + strength > .75
|
||||
|
||||
server_centrality <- arrow::read_ipc_file("data/scratch/server_centrality.feather") %>%
|
||||
rename(generality = strength)
|
||||
|
||||
sel_a <- a %>%
|
||||
mutate(is_ms = server == "mastodon.social") %>%
|
||||
mutate(general = server %in% general_servers) %>%
|
||||
ungroup() %>%
|
||||
inner_join(server_summary, by = "server") %>%
|
||||
inner_join(server_summary, by = "server") %>%
|
||||
left_join(server_centrality, by = "server") %>%
|
||||
mutate(small_server = user_count <= 100) %>%
|
||||
mutate(large_server = user_count >= 1000) %>%
|
||||
#filter(jm) %>%
|
||||
@ -88,3 +92,7 @@ plot_km <- sel_a %>%
|
||||
scale_color_discrete(name = "Group", labels = c("Other JoinMastodon", "General")) +
|
||||
theme_bw_small_labels() +
|
||||
theme(axis.text.x = element_text(angle = 45, hjust = 1), legend.position="bottom")
|
||||
|
||||
# logistic regression on generality
|
||||
logit <- sel_a %>%
|
||||
glm(active ~ generality, data = ., family = "binomial")
|
||||
@ -1,154 +0,0 @@
|
||||
---
|
||||
title: "Do Servers Matter on Mastodon? Data-driven Design for Decentralized Social Media"
|
||||
author: Carl Colglazier
|
||||
bibliography: references.bib
|
||||
format:
|
||||
ic2s2-pdf: default
|
||||
execute:
|
||||
echo: false
|
||||
error: false
|
||||
warning: false
|
||||
message: false
|
||||
cache: true
|
||||
knitr:
|
||||
opts_knit:
|
||||
verbose: true
|
||||
---
|
||||
|
||||
```{r, cache.extra = tools::md5sum("code/helpers.R")}
|
||||
#| label: fig-account-timeline
|
||||
#| fig-cap: "Accounts in the dataset created between January 2022 and March 2023. The top panels shows the proportion of accounts still active 45 days after creation, the proportion of accounts that have moved, and the proportion of accounts that have been suspended. The bottom panel shows the count of accounts created each week. The dashed vertical lines in the bottom panel represent the annoucement day of the Elon Musk Twitter acquisition, the acquisition closing day, a day where Twitter suspended a number of prominent journalist, and a day when Twitter experienced an outage and started rate limiting accounts."
|
||||
#| fig-height: 2.75
|
||||
#| fig-width: 6.75
|
||||
#| fig-env: figure*
|
||||
#| fig-pos: tb!
|
||||
|
||||
library(here)
|
||||
source(here("code/helpers.R"))
|
||||
account_timeline_plot()
|
||||
```
|
||||
|
||||
Following Twitter's 2022 acquisition, Mastodon---an open-source, decentralized social network and microblogging community---saw an increase in activity and attention as a potential Twitter alternative [@heFlockingMastodonTracking2023; @cavaDriversSocialInfluence2023]. While millions of people set up new accounts and significantly increased the size of the network (@fig-account-timeline), many of these newcomers and potential newcomers found the process confusing and many accounts did not remain active. Unlike centralized social media platforms, Mastodon is a network of independent servers with their own rules and norms [@nicholsonMastodonRulesCharacterizing2023]. Each server can communicate with each other using the shared ActivityPub protocols and accounts can move between Mastodon servers, but the local experience can vary widely from server to server.
|
||||
|
||||
Although attracting and retaining newcomers is a key challenge for online communities [@krautBuildingSuccessfulOnline2011 p. 182], Mastodon's onboarding process has not always been straightforward. Variation among servers can also present a challenge for newcomers who may not even be aware of the specific rules, norms, or general topics of interest on the server they are joining [@diazUsingMastodonWay2022]. Further, many Mastodon servers have specific norms which people coming from Twitter may find confusing, such as local norms around content warnings [@nicholsonMastodonRulesCharacterizing2023]. Various guides and resources for people trying to join Mastodon offered mixed advice on choosing a server. Some suggest that the most important thing is to simply join any server and work from there [@krasnoffMastodon101How2022; @silberlingBeginnerGuideMastodon2023], while others have created tools and guides to help people find potential servers of interest by size and location[@thekinrarMastodonInstances; @kingMastodonMe2024].
|
||||
|
||||
Mastodon's approach to onboarding has also changed over time. In much of 2020 and early 2021, the Mastodon developers closed signups to their flagship server and linked to an alternative server, which saw increased sign-ups during this period. They also linked to a list of servers on the Join Mastodon webpage [@mastodonggmbhServers], where all servers are pre-approved and follow the Mastodon Server Covenant which guarantees certain content moderation standards and data protections. Starting in 2023, the Mastodon developers shifted toward making the flagship server the default when people sign up on the official Mastodon Android and iOS apps [@rochkoNewOnboardingExperience2023; @rothItGettingEasier2023].
|
||||
|
||||
We first ask question: *Does server choice matter for Mastodon newcomers?* Toward this question, we used profile data from over a million Mastodon accounts collected from public timelines and profile directories between October 1, 2020 and August 15, 2023. With a subset of these accounts created from May 1 to June 30, 2023, we create a Kaplan–Meier estimator for account activity in the 91 days after creation (@fig-survival). We find that accounts on the 12 largest general instances featured at the top of the Join Mastodon webpage (which includes the flagship server) are less likely to remain active than accounts created on other Join Mastodon servers.
|
||||
|
||||
To corroborate this model, we also use data from thousands of accounts which moved between Mastodon servers, taking advantage of the data portability of the platform. Conceiving of these moved accounts as edges within a weighted directional network where nodes represent servers, edges represent accounts, and weights represent the number of accounts that moved between servers, we construct an exponential family random graph model (ERGM) with terms for server size, open registrations, and language match between servers. We find that accounts are more likely to move from larger servers to smaller servers.
|
||||
|
||||
```{=html}
|
||||
<!--
|
||||
We found that users who sign up on large, general topic servers are less likely to remain active than those who sign up on smaller servers. We also found that many users who move their accounts between servers tend to gravitate toward smaller servers over time.
|
||||
-->
|
||||
```
|
||||
Based on these findings, we suggest a need for better ways for potential newcomers to find servers and propose a viable way to create server and tag recommendations on Mastodon, which could both help newcomers find servers that match their interests and help established accounts discover "neighborhoods" of related servers. One challenge in building such a system is the decentralized nature of the system. A single, central actor which collects data from servers and then distributes recommendations would be antithetical to the decentralized nature of Mastodon. Instead, we propose a system where servers can report the top hashtags by the number of unique accounts on the server using them during the last three months. Such a system would be opt-in and require few additional server resources since tags already have their own database table.
|
||||
|
||||
In our proposal, after collecting these top tags on each server, each server then uses Okapi BM25 to construct a term frequency-inverse document frequency (TF-IDF) matrix to associate the top tags with each server in their known network. We suggest first filtering to only consider tags used by a minimal number of account on a server and only consider tags used on a minimal number of servers. The counts of tag-account pairs from each server make up the term frequency and the number of servers that use each tag make up the inverse document frequency. The system can then apply L2 normalization to the vectors for each tag and calculate the cosine similarity between the tag vectors for each server. To find similarity between tags, the system could also calculate the cosine similarity between the server vectors.
|
||||
|
||||
To determine the viability of the recommendation system, we simulated various scenarios that limit both servers that report data and the number of tags they report. We used rank biased overlap (RBO) to then compare the outputs from these simulations to the baseline with more complete information from all tags on all servers. @fig-simulations-rbo shows how the average agreement with the baseline scales linearly with the logarithm of the tag count.
|
||||
|
||||
Thus based on analysis of trace data from millions of new Mastodon accounts, we find evidence that suggests that servers matter and that users tend to move from larger servers to smaller servers. We then propose a recommendation system that can help new Mastodon users find servers with a high probability of being a good match based on their interests. Based on simulations, we demonstrate that such a tool can be effectively deployed in a federated manner, even with limited data on each local server.
|
||||
|
||||
```{r, cache.extra = tools::md5sum("code/survival.R")}
|
||||
#| cache: true
|
||||
#| label: fig-survival
|
||||
#| fig-cap: "Survival probabilities for accounts created during May and June 2023 on servers featured on Join Mastodon. Groups represent whether the account is on one of the 12 largest and most prominently featured servers or another Join Mastodon server."
|
||||
library(here)
|
||||
source(here("code/survival.R"))
|
||||
plot_km
|
||||
```
|
||||
|
||||
::: {#tbl-ergm-table}
|
||||
```{r}
|
||||
#| label: table-ergm-table
|
||||
#| echo: false
|
||||
#| warning: false
|
||||
#| message: false
|
||||
#| error: false
|
||||
|
||||
library(here)
|
||||
library(modelsummary)
|
||||
library(kableExtra)
|
||||
library(purrr)
|
||||
library(stringr)
|
||||
load(file = here("data/scratch/ergm-model-early.rda"))
|
||||
load(file = here("data/scratch/ergm-model-late.rda"))
|
||||
|
||||
x <- modelsummary(
|
||||
list("Coef." = model.early, "Std.Error" = model.early, "Coef." = model.late, "Std.Error" = model.late),
|
||||
estimate = c("{estimate}", "{stars}{std.error}", "{estimate}", "{stars}{std.error}"),
|
||||
statistic = NULL,
|
||||
gof_omit = ".*",
|
||||
coef_rename = c(
|
||||
"sum" = "Sum",
|
||||
"nonzero" = "Nonzero",
|
||||
"diff.sum0.h-t.accounts" = "Smaller server",
|
||||
"nodeocov.sum.accounts" = "Server size\n(outgoing)",
|
||||
"nodeifactor.sum.registrations.TRUE" = "Open registrations\n(incoming)",
|
||||
"nodematch.sum.language" = "Languages match"
|
||||
),
|
||||
align="lrrrr",
|
||||
stars = c('*' = .05, '**' = 0.01, '***' = .001),
|
||||
output = "latex_tabular"
|
||||
#output = "markdown",
|
||||
#table.envir='table*',
|
||||
#table.env="table*"
|
||||
) %>% add_header_above(c(" " = 1, "Model A" = 2, "Model B" = 2))
|
||||
|
||||
x
|
||||
```
|
||||
|
||||
Exponential family random graph models for account movement between Mastodon servers. Accounts in Model A were created in May 2022 and moved to another account at some later point. Accounts in Model B were created at some earlier point and moved after October 2023.
|
||||
:::
|
||||
|
||||
::: {#tbl-sim-servers}
|
||||
```{r}
|
||||
#| label: table-sim-servers
|
||||
library(tidyverse)
|
||||
library(arrow)
|
||||
|
||||
sim_servers <- "data/scratch/server_similarity.feather" %>% arrow::read_ipc_file()
|
||||
server_of_interest <- "hci.social"
|
||||
server_table <- sim_servers %>%
|
||||
arrange(desc(Similarity)) %>%
|
||||
filter(Source == server_of_interest | Target == server_of_interest) %>%
|
||||
head(5) %>%
|
||||
pivot_longer(cols=c(Source, Target)) %>%
|
||||
filter(value != server_of_interest) %>%
|
||||
select(value, Similarity) %>%
|
||||
rename("Server" = "value")
|
||||
|
||||
if (knitr::is_latex_output()) {
|
||||
server_table %>% knitr::kable(format="latex", booktabs=TRUE, digits=3)
|
||||
} else {
|
||||
server_table %>% knitr::kable(digits = 3)
|
||||
}
|
||||
```
|
||||
|
||||
Top five servers most similar to hci.social, a Mastodon server focused on human-computer interaction research. Each of these servers relate to computer science, academia, or technology.
|
||||
:::
|
||||
|
||||
```{r}
|
||||
#| label: fig-simulations-rbo
|
||||
#| fig-env: figure*
|
||||
#| cache: true
|
||||
#| fig-width: 6.75
|
||||
#| fig-height: 3
|
||||
#| fig-pos: tb
|
||||
#| fig-cap: "Simulated rank biased overlap between simulated server similarity ranks varied by the number of tags reported by each server and the number of servers that report data. The baseline uses 256 tags."
|
||||
library(tidyverse)
|
||||
library(arrow)
|
||||
simulations <- arrow::read_ipc_file("data/scratch/simulation_rbo.feather")
|
||||
|
||||
simulations %>%
|
||||
group_by(servers, tags, run) %>% summarize(rbo=mean(rbo), .groups="drop") %>%
|
||||
mutate(ltags = as.integer(log2(tags))) %>%
|
||||
ggplot(aes(x = factor(ltags), y = rbo, fill = factor(ltags))) +
|
||||
geom_boxplot() +
|
||||
facet_wrap(~servers, nrow=1) +
|
||||
#scale_y_continuous(limits = c(0, 1)) +
|
||||
labs(x = "Tags (log2)", y = "RBO", title = "Rank Biased Overlap with Baseline Rankings by Number of Servers") +
|
||||
theme_minimal() + theme(legend.position = "none")
|
||||
```
|
||||
473
icwsm.qmd
473
icwsm.qmd
@ -1,473 +0,0 @@
|
||||
---
|
||||
title: "Do Servers Matter on Mastodon? Data-driven Design for Decentralized Social Media"
|
||||
short-title: Mastodon Recommendations
|
||||
authors:
|
||||
- name: Carl Colglazier
|
||||
affiliation:
|
||||
name: Northwestern University
|
||||
city: Evanston
|
||||
state: Illinois
|
||||
country: United States
|
||||
corresponding: true
|
||||
bibliography: references.bib
|
||||
pdf-engine: pdflatex
|
||||
format:
|
||||
pdf:
|
||||
output-file: mastodon-recommendations-icwsm.pdf
|
||||
fig-pos: 'ht!bp'
|
||||
cite-method: natbib
|
||||
template: template.tex
|
||||
keep-md: true
|
||||
link-citations: false
|
||||
abstract: |
|
||||
When trying to join Mastodon, a decentralized collection of interoperable social networking servers, new users face the dilemma of choosing a home server. Using trace data from millions of new Mastodon accounts, we show that new accounts are less likely to remain active on the network's largest general instances compared to others. Additionally, we observe a trend of users migrating from larger to smaller servers. Addressing the challenge of onboarding and server selection, the paper proposes a decentralized recommendation system for server using hashtags and the Okapi BM25 algorithm. This system leverages servers' top hashtags and their frequency to create a recommendation mechanism that respects Mastodon's decentralized ethos.
|
||||
execute:
|
||||
echo: false
|
||||
error: false
|
||||
warning: false
|
||||
message: false
|
||||
freeze: false
|
||||
cache: true
|
||||
fig-width: 6.75
|
||||
knitr:
|
||||
opts_knit:
|
||||
verbose: true
|
||||
---
|
||||
|
||||
```{r}
|
||||
#| label: setup
|
||||
|
||||
profile <- Sys.getenv("QUARTO_PROFILE", unset="acm")
|
||||
if (profile == "acm") {
|
||||
class_wide <- ".column-body"
|
||||
} else {
|
||||
class_wide <- ".column-page"
|
||||
}
|
||||
|
||||
envs <- Sys.getenv()
|
||||
```
|
||||
|
||||
# Introduction
|
||||
|
||||
Following Twitter's 2022 acquisition, Mastodon---an open-source, decentralized social network and microblogging community---saw an increase in activity and attention as a potential Twitter alternative [@heFlockingMastodonTracking2023; @lacavaDriversSocialInfluence2023]. While millions of new accounts significantly increased the size of the network, many newcomers found the process confusing and did not remain active. Unlike centralized social media platforms, Mastodon is a network of independent servers, each with their own rules and norms [@nicholsonMastodonRulesCharacterizing2023], which can communicate with each other using the shared ActivityPub protocols. Athough accounts can move between Mastodon servers, the local experience can vary widely from server to server.
|
||||
|
||||
Attracting and retaining newcomers is a key challenge for online communities [@krautBuildingSuccessfulOnline2011 p. 182]. On Mastodon, the onboarding process has not always been straightforward: variation among servers mean newcomers who may not even be aware of the specific rules, norms, or general topics of interest on the server they are joining [@diazUsingMastodonWay2022]. Various guides and resources for people trying to join Mastodon offered mixed advice on choosing a server. Some suggest that the most important thing is to simply join any server and work from there [@krasnoffMastodon101How2022; @silberlingBeginnerGuideMastodon2023]; others have created tools and guides to help people find potential servers of interest by size and location[@thekinrarMastodonInstances2017; @kingMastodonMe2024].
|
||||
|
||||
Mastodon's decentralized design has long been in tension with the disproportionate popularity of a small set of large, general-topic servers within the system [@ramanChallengesDecentralisedWeb2019a]. Analysing the activity of new accounts that join the network, we find that users who sign up on such servers are less likely to remain active after 91 days. We also find that users who move accounts tend to gravitate toward smaller, more niche servers over time, suggesting that established users may also find additional utility from such servers.
|
||||
|
||||
In response to these findings, we propose a potential extension to Mastodon to facilitate server and tag recommendations by having each server report their most popular local hashtags. This recommendation system could both help newcomers find servers that match their interests and help established accounts discover "neighborhoods" of related servers.
|
||||
|
||||
# Background
|
||||
|
||||
## Empirical Setting
|
||||
|
||||
The Fediverse is a set of decentralized online social networks which interoperate using shared protocols like ActivityPub. Mastodon is a software program used by many Fediverse servers and offers a user experience similar to the Tweetdeck client for Twitter. It was first created in late 2016 and saw a surge in interest in 2022 during and after Elon Musk's Twitter acquisition.
|
||||
|
||||
Mastodon features three kinds of timelines: a "home" timeline which shows all posts from accounts followed by the user; a "local" timeline which shows all public posts from the local server; and a "federated" timeline which includes all posts from users followed by other users on their server. The local timeline is unique to each server. On larger servers, this timeline can be unwieldy; however, on smaller servers, it presents the opportunity to discover new posts and users of potential interest.
|
||||
|
||||
Discovery has been challenging on Mastodon. Text search, for instance, was impossible on most servers until support for this feature was added on an optional, opt-in basis using Elasticsearch in late 2023 [@rochkoMastodon2023]. Recommendation systems are currently a somewhat novel problem in the context of decentralized online social networks. @trienesRecommendingUsersWhom2018 developed a recommendation system for finding new accounts to follow on the Fediverse which used collaborative filtering based on BM25 in an early example of a content discovery system on Mastodon.
|
||||
|
||||
Individual Mastodon servers can have an effect on the end experience of users. For example, some servers may choose to federate with some servers but not others, altering the topology of the Fediverse network for their users. At the same time, accounts need to be locked into one specific server. Because of Mastodon's data portability, users can move their accounts freely between servers while retaining their followers, though their post history remains with their original account.
|
||||
|
||||
## The Mastodon Migrations
|
||||
|
||||
Mastodon saw a surge in interest in 2022 and 2023, particularly after Elon Musk's Twitter acquisition. In particular, four events of interests drove measurable increases in new users to the network: the announcement of the acquisition (April 14, 2022), the closing of the acquisition (October 27, 2022), a day when Twitter suspended a number of prominent journalists (December 15, 2022), and a day when Twitter experienced an outage and started rate limiting accounts (July 1, 2023). Many Twitter accounts announced they were setting up Mastodon accounts and linked their new accounts to their followers, often using tags like #TwitterMigration [@heFlockingMastodonTracking2023] and driving interest in Mastodon in a process @lacavaDriversSocialInfluence2023 found consistent with social influence theory.
|
||||
|
||||
Despite the influx of users, not all of these new accounts remained active. As such, some media outlets have framed reports on Mastodon [@hooverMastodonBumpNow2023] through what @zulliRethinkingSocialSocial2020 calls the "Killer Hype Cycle", whereby the media finds a new alternative social media platform, declares it a potential killer of some established platform, and later calls it a failure if it does not displace the existing platform. Such framing fails to take systems like the Fediverse seriously for their own merits: completely replacing existing commercial systems is not the only way to measure success, nor does it account for the real value the Fediverse provides for its millions of active users.
|
||||
|
||||
Mastodon's approach to onboarding has changed over time. In much of 2020 and early 2021, the Mastodon developers closed sign-ups to their flagship server and linked to an alternative server, which saw increased sign-ups during this period. They also linked to a list of servers on the "Join Mastodon" webpage[^2], where all servers are pre-approved and follow the Mastodon Server Covenant which guarantees certain content moderation standards and data protections. Starting in 2023, the Mastodon developers shifted toward making the flagship server the default when people sign up on the official Mastodon Android and iOS apps [@rochkoNewOnboardingExperience2023; @rothItGettingEasier2023]. These changes suggest that removing friction to onboarding is an increasing priority for the Mastodon developers.
|
||||
|
||||
[^2]: https://joinmastodon.org/servers
|
||||
|
||||
## Newcomers in Online Communities
|
||||
|
||||
Onboarding newcomers is an important part of the life cycle of online communities. Any community can expect a certain amount of turnover, and so it is important for the long-term health and longevity of the community to be able to bring in new members [@krautBuildingSuccessfulOnline2011 p. 182]. However, the process of onboarding newcomers is not always straightforward.
|
||||
|
||||
The series of migrations of new users into Mastodon in many ways reflect folk stories of "Eternal Septembers" on previous communication networks, where a large influx of newcomers challenged the existing norms [@driscollWeMisrememberEternal2023; @kieneSurvivingEternalSeptember2016]. Many Mastodon servers do have specific norms which people coming from Twitter may find confusing, such as local norms around content warnings [@nicholsonMastodonRulesCharacterizing2023]. Variation among servers can also present a challenge for newcomers who may not even be aware of the specific rules, norms, or general topics of interest on the server they are joining [@diazUsingMastodonWay2022]. Mastodon servers open to new accounts must thus be both accommodating to newcomers while at the same ensuring the propagation of their norms and culture, either through social norms or through technical means.
|
||||
|
||||
# Data
|
||||
|
||||
```{r}
|
||||
#| label: fig-account-timeline
|
||||
#| fig-cap: "Accounts in the dataset created between January 2022 and March 2023. The top panels shows the proportion of accounts still active 45 days after creation, the proportion of accounts that have moved, and the proportion of accounts that have been suspended. The bottom panel shows the count of accounts created each week. The dashed vertical lines in the bottom panel represent the annoucement day of the Elon Musk Twitter acquisition, the acquisition closing day, a day where Twitter suspended a number of prominent journalist, and a day when Twitter experienced an outage and started rate limiting accounts."
|
||||
#| fig-height: 2.75
|
||||
#| fig-width: 6.75
|
||||
#| fig-env: figure*
|
||||
#| fig-pos: tb!
|
||||
|
||||
library(here)
|
||||
source(here("code/helpers.R"))
|
||||
account_timeline_plot()
|
||||
```
|
||||
|
||||
Mastodon has an extensive API which allows for the collection of public posts and account information. We collected data from the public timelines of Mastodon servers using the Mastodon API with a crawler which runs once per day. We also collected account information from the opt-in public profile directories on these servers.
|
||||
|
||||
```{r}
|
||||
#| label: data-counts
|
||||
#| cache: true
|
||||
|
||||
library(arrow)
|
||||
library(tidyverse)
|
||||
library(here)
|
||||
source(here("code/helpers.R"))
|
||||
|
||||
accounts <- load_accounts(filt = FALSE) %>%
|
||||
filter(created_at >= "2020-08-14") %>%
|
||||
filter(created_at < "2024-01-01")
|
||||
|
||||
tag_posts <- "data/scratch/all_tag_posts.feather" %>%
|
||||
arrow::read_ipc_file(. , col_select = c("host", "acct", "created_at")) %>%
|
||||
filter(created_at >= as.Date("2023-05-01")) %>%
|
||||
filter(created_at < as.Date("2023-08-01"))
|
||||
|
||||
text_format <- function(df) {
|
||||
return (format(nrow(df), big.mark=","))
|
||||
}
|
||||
|
||||
num_tag_posts <- tag_posts %>% text_format()
|
||||
num_tag_accounts <- tag_posts %>% distinct(host, acct) %>% text_format()
|
||||
num_tag_servers <- tag_posts %>% distinct(host) %>% text_format()
|
||||
|
||||
num_accounts_unfilt <- accounts %>% text_format()
|
||||
num_account_bots <- accounts %>% filter(bot) %>% text_format()
|
||||
num_account_nostatuses <- accounts %>% filter(is.na(last_status_at)) %>% text_format()
|
||||
num_account_suspended <- accounts %>% mutate(suspended = replace_na(suspended, FALSE)) %>% filter(suspended) %>% text_format()
|
||||
num_accounts_moved <- accounts %>% filter(has_moved) %>% text_format()
|
||||
num_account_limited <- accounts %>% filter(limited) %>% text_format()
|
||||
num_account_samedaystatus <- accounts %>% filter(last_status_at <= created_at) %>% text_format()
|
||||
num_account_filt <- load_accounts(filt = TRUE) %>% text_format()
|
||||
```
|
||||
|
||||
**Mastodon Profiles**: We collected accounts using data previously collected from posts on public Mastodon timelines from October 2020 to August 2023. We then queried for up-to-date information on those accounts including their most recent status and if the account had moved as of February 2024. Through this process, we discovered a total of `r num_accounts_unfilt` account created between August 14, 2020 and January 1, 2024. We then filtered out accounts which were bots (`r num_account_bots` accounts), had been suspended (`r num_account_suspended` accounts), had been marked as moved to another account (`r num_accounts_moved` accounts), had been limited by their local server (`r num_account_limited` accounts), had no statuses (`r num_account_nostatuses` accounts), or had posted their last status on the same day as their account creation (`r num_account_samedaystatus` accounts). This gave us a total of `r num_account_filt` accounts which met all the filtering criteria. Note that because we got updated information on each account, we include only accounts on servers which still existed at the time of our profile queries and which returned records for the account.
|
||||
|
||||
**Tags**: Mastodon supports hashtags, which are user-generated metadata tags that can be added to posts. Clicking the link for a tag shows a stream of posts which also have that tag from the federated timeline, which includes accounts on the same server and posts from accounts followed by the accounts on the local server. We collected `r num_tag_posts` statuses posted by `r num_tag_accounts` accounts on `r num_tag_servers` unique servers from between May to July 2023 which contained at least one hashtag.
|
||||
|
||||
# Analysis and Results
|
||||
|
||||
## Survival Model
|
||||
|
||||
*Are accounts on suggested general servers less likely to remain active than accounts on other servers?*
|
||||
|
||||
```{r, cache.extra = tools::md5sum("code/survival.R")}
|
||||
#| cache: true
|
||||
#| label: fig-survival
|
||||
#| fig-env: figure
|
||||
#| fig-cap: "Survival probabilities for accounts created during May 2023."
|
||||
#| fig-width: 3.375
|
||||
#| fig-height: 2.5
|
||||
#| fig-pos: h!
|
||||
|
||||
library(here)
|
||||
source(here("code/survival.R"))
|
||||
plot_km
|
||||
```
|
||||
|
||||
```{r}
|
||||
#| label: table-coxme
|
||||
library(ehahelper)
|
||||
library(broom)
|
||||
|
||||
cxme_table <- tidy(cxme) %>%
|
||||
mutate(conf.low = exp(conf.low), conf.high=exp(conf.high)) %>%
|
||||
mutate(term = case_when(
|
||||
term == "factor(group)1" ~ "Join Mastodon",
|
||||
term == "factor(group)2" ~ "General Servers",
|
||||
term == "small_serverTRUE" ~ "Small Server",
|
||||
TRUE ~ term
|
||||
)) %>%
|
||||
mutate(exp.coef = paste("(", round(conf.low, 2), ", ", round(conf.high, 2), ")", sep="")) %>%
|
||||
select(term, estimate, exp.coef , p.value)
|
||||
```
|
||||
|
||||
Using `r text_format(sel_a)` accounts created from May 1 to June 30, 2023, we create a Kaplan–Meier estimator for the probability that an account will remain active based on whether the account is on one of the largest general instances [^1] featured at the top of the Join Mastodon webpage or otherwise if it is on a server in the Join Mastodon list. Accounts are considered active if they have made at least one post after the censorship period `r active_period` days after account creation.
|
||||
|
||||
[^1]: `r paste(general_servers, collapse=", ")`
|
||||
|
||||
::: {.content-visible unless-profile="icwsm"}
|
||||
|
||||
::: {#tbl-cxme .column-body}
|
||||
```{r}
|
||||
if (knitr::is_latex_output()) {
|
||||
cxme_table %>% knitr::kable(format="latex", booktabs=TRUE, digits=3)
|
||||
} else {
|
||||
cxme_table %>% knitr::kable(digits = 3)
|
||||
}
|
||||
```
|
||||
|
||||
Coefficients for the Cox Proportional Hazard Model with Mixed Effects. The model includes a random effect for the server.
|
||||
|
||||
:::
|
||||
|
||||
|
||||
We also construct a Mixed Effects Cox Proportional Hazard Model
|
||||
|
||||
$$
|
||||
h(t_{ij}) = h_0(t) \exp\left(\begin{aligned}
|
||||
&\beta_1 \text{Join Mastodon} \\
|
||||
&+ \beta_2 \text{General Servers} \\
|
||||
&+ \beta_3 \text{Small Server} \\
|
||||
&+ b_{j}
|
||||
\end{aligned}\right)
|
||||
$$
|
||||
|
||||
where $h(t_{ij})$ is the hazard for account $i$ on server $j$ at time $t$, $h_0(t)$ is the baseline hazard, $\beta_1$ is the coefficient for whether the account is on a server featured on Join Mastodon, $\beta_2$ is the coefficient for whether the account is on one of the largest general instances, $\beta_3$ is the coefficient for whether the account is on a small server with less than 100 accounts, and $b_{j}$ is the random effect for server $j$.
|
||||
|
||||
<!-- with coefficients for whether the account is on a small server (less than a hundred accounts), and whether the account in featured on JoinMastodon or is featured as one of the largest general instances. -->
|
||||
|
||||
We again find that accounts on the largest general instances are less likely to remain active than accounts on other servers, while accounts created on smaller servers are more likely to remain active.
|
||||
|
||||
:::
|
||||
|
||||
## Moved Accounts
|
||||
|
||||
*Do accounts tend to move to larger or smaller servers?*
|
||||
|
||||
Mastodon users can move their accounts to another server while retaining their connections (but not their posts) to other Mastodon accounts. This feature, built into the Mastodon software, offers data portability and helps avoid lock-in.
|
||||
|
||||
```{r}
|
||||
#| label: table-ergm-table
|
||||
#| echo: false
|
||||
#| warning: false
|
||||
#| message: false
|
||||
#| error: false
|
||||
|
||||
library(here)
|
||||
library(modelsummary)
|
||||
library(kableExtra)
|
||||
library(purrr)
|
||||
library(stringr)
|
||||
load(file = here("data/scratch/ergm-model-early.rda"))
|
||||
load(file = here("data/scratch/ergm-model-late.rda"))
|
||||
|
||||
if (knitr::is_latex_output()) {
|
||||
format <- "latex_tabular"
|
||||
} else {
|
||||
format <- "html"
|
||||
}
|
||||
|
||||
x <- modelsummary(
|
||||
list("Coef." = model.early, "Std.Error" = model.early),#, "Coef." = model.late, "Std.Error" = model.late),
|
||||
estimate = c("{estimate}", "{stars}{std.error}"),# "{estimate}", "{stars}{std.error}"),
|
||||
statistic = NULL,
|
||||
gof_omit = ".*",
|
||||
coef_rename = c(
|
||||
"sum" = "Sum",
|
||||
"nonzero" = "Nonzero",
|
||||
"diff.sum0.h-t.accounts" = "Smaller server",
|
||||
"nodeocov.sum.accounts" = "Server size\n(outgoing)",
|
||||
"nodeifactor.sum.registrations.TRUE" = "Open registrations\n(incoming)",
|
||||
"nodematch.sum.language" = "Languages match"
|
||||
),
|
||||
align="lrr",
|
||||
stars = c('*' = .05, '**' = 0.01, '***' = .001),
|
||||
output = format
|
||||
)# %>% add_header_above(c(" " = 1, "Model A" = 2, "Model B" = 2))
|
||||
```
|
||||
|
||||
:::: {#tbl-ergm-table }
|
||||
|
||||
```{r}
|
||||
x # `r class_wide`
|
||||
```
|
||||
|
||||
Exponential family random graph models for account movement between Mastodon servers. Accounts were created in May 2022 and moved to another account at some later point.
|
||||
|
||||
::::
|
||||
|
||||
To corroborate our findings, we also use data from thousands of accounts which moved between Mastodon servers, taking advantage of the data portability of the platform. Conceiving of these moved accounts as edges within a weighted directional network where nodes represent servers, edges represent accounts, and weights represent the number of accounts that moved between servers, we construct an exponential family random graph model (ERGM) with terms for server size, open registrations, and language match between servers. We find that accounts are more likely to move from larger servers to smaller servers.
|
||||
|
||||
|
||||
# Proposed Recommendation System
|
||||
|
||||
*How can we build an opt-in, low-resource recommendation system for finding Fediverse servers?*
|
||||
|
||||
Based on these findings, we suggest a need for better ways for newcomers to find servers and propose a viable way to create server and tag recommendations on Mastodon. This system could both help newcomers find servers that match their interests and help established accounts discover "neighborhoods" of related servers.
|
||||
|
||||
One challenge in building such a system is the decentralized nature of the system. A single, central actor which collects data from servers and then distributes recommendations would be antithetical to the decentralized nature of Mastodon. Instead, we propose a system where servers can report the top hashtags by the number of unique accounts on the server using them during the last three months. Such a system would be opt-in and require few additional server resources since tags already have their own database table.
|
||||
|
||||
## Recommendation System Design
|
||||
|
||||
We use Okapi BM25 to construct a term frequency-inverse document frequency (TF-IDF) model to associate the top tags with each server using counts of tag-account pairs from each server for the term frequency and the number of servers that use each tag for the inverse document frequency. We then L2 normalize the vectors for each tag and calculate the cosine similarity between the tag vectors for each server.
|
||||
|
||||
$$
|
||||
tf = \frac{f_{t,s} \cdot (k_1 + 1)}{f_{t,s} + k_1 \cdot (1 - b + b \cdot \frac{|s|}{avgstl})}
|
||||
$$
|
||||
|
||||
where $f_{t,s}$ is the number of accounts using the tag $t$ on server $d$, $k_1$ and $b$ are tuning parameters, and $avgstl$ is the average sum of account-tag pairs. For the inverse document frequency, we use the following formula:
|
||||
|
||||
$$
|
||||
idf = \log \frac{N - n + 0.5}{n + 0.5}
|
||||
$$
|
||||
|
||||
where $N$ is the total number of servers and $n$ is the number of servers where the tag appears as one of the top tags. We then apply L2 normalization:
|
||||
|
||||
$$
|
||||
tfidf = \frac{tf \cdot idf}{\| tf \cdot idf \|_2}
|
||||
$$
|
||||
|
||||
## Applications
|
||||
|
||||
```{r}
|
||||
#| eval: false
|
||||
library(tidyverse)
|
||||
library(igraph)
|
||||
library(arrow)
|
||||
|
||||
sim_servers <- "data/scratch/server_similarity.feather" %>% arrow::read_ipc_file() %>% rename("weight" = "Similarity")
|
||||
#sim_net <- as.network(sim_servers)
|
||||
g <- graph_from_data_frame(sim_servers, directed = FALSE)
|
||||
|
||||
g_strength <- log(sort(strength(g)))
|
||||
normalized_strength <- (g_strength - min(g_strength)) / (max(g_strength) - min(g_strength))
|
||||
|
||||
server_centrality <- enframe(normalized_strength, name="server", value="strength")
|
||||
server_centrality %>% arrow::write_ipc_file("data/scratch/server_centrality.feather")
|
||||
```
|
||||
|
||||
### Server Similarity Neighborhoods
|
||||
|
||||
Mastodon provides two feeds in addition to a user's home timeline populated by accounts they follow: a local timeline with all public posts from their local server and a federated timeline which includes all posts from users followed by other users on their server. We suggest a third kind of timeline, a *neighborhood timeline*, which filters the federated timeline by topic. We calculate the pairwise similarity between two servers using cosine similarity.
|
||||
|
||||
::: {#tbl-sim-servers .content-visible unless-profile="icwsm"}
|
||||
|
||||
```{r}
|
||||
#| label: table-sim-servers
|
||||
library(tidyverse)
|
||||
library(arrow)
|
||||
|
||||
sim_servers <- "data/scratch/server_similarity.feather" %>% arrow::read_ipc_file()
|
||||
server_of_interest <- "hci.social"
|
||||
server_table <- sim_servers %>%
|
||||
arrange(desc(Similarity)) %>%
|
||||
filter(Source == server_of_interest | Target == server_of_interest) %>%
|
||||
head(5) %>%
|
||||
pivot_longer(cols=c(Source, Target)) %>%
|
||||
filter(value != server_of_interest) %>%
|
||||
select(value, Similarity) %>%
|
||||
rename("Server" = "value")
|
||||
|
||||
if (knitr::is_latex_output()) {
|
||||
server_table %>% knitr::kable(format="latex", booktabs=TRUE, digits=3)
|
||||
} else {
|
||||
server_table %>% knitr::kable(digits = 3)
|
||||
}
|
||||
```
|
||||
|
||||
Top five servers most similar to hci.social
|
||||
|
||||
:::
|
||||
|
||||
### Tag Similarity
|
||||
|
||||
We also calculate the similarity between tags using the same method. This can be used to suggest related tags to users based on their interests or tags related to already selected tags in the recommendation system.
|
||||
|
||||
### Server Discovery
|
||||
|
||||
Given a set of popular tags and a list of servers, we build a recommendation system[^rec] where users select tags from a list of popular tags and receive server suggestions. The system first creates a subset of vectors based on the TF-IDF matrix which represents the top clusters of topics. After a user selects the top tags of interest to them, it suggests servers which match their preferences using the singular value decomposition (SVD) of the TF-IDF matrix.
|
||||
|
||||
[^rec]: A live demo for the system is availible at https://carlcolglazier.com/demos/deweb2024/
|
||||
|
||||
::: {.content-visible unless-profile="icwsm"}
|
||||
|
||||
## Rubustness to Limited Data
|
||||
|
||||
```{r}
|
||||
#| label: fig-simulations-rbo
|
||||
#| fig-env: figure*
|
||||
#| cache: true
|
||||
#| fig-width: 6.75
|
||||
#| fig-height: 3
|
||||
#| fig-pos: tb
|
||||
library(tidyverse)
|
||||
library(arrow)
|
||||
simulations <- arrow::read_ipc_file("data/scratch/simulation_rbo.feather")
|
||||
|
||||
simulations %>%
|
||||
group_by(servers, tags, run) %>% summarize(rbo=mean(rbo), .groups="drop") %>%
|
||||
mutate(ltags = as.integer(log2(tags))) %>%
|
||||
ggplot(aes(x = factor(ltags), y = rbo, fill = factor(ltags))) +
|
||||
geom_boxplot() +
|
||||
facet_wrap(~servers, nrow=1) +
|
||||
#scale_y_continuous(limits = c(0, 1)) +
|
||||
labs(x = "Tags (log2)", y = "RBO", title = "Rank Biased Overlap with Baseline Rankings by Number of Servers") +
|
||||
theme_minimal() + theme(legend.position = "none")
|
||||
```
|
||||
|
||||
A challenge for a federated recommendation system like we propose is that it needs buy in from a sufficient number of servers to provide value. There is also a tradeoff between the amount of tags to expose for each server and potential concerns about exposing too much data.
|
||||
|
||||
We simulated various scenarios that limit both servers that report data and the number of tags they report. We used rank biased overlap (RBO) to then compare the outputs from these simulations to the baseline with more complete information from all tags on all servers [@webberSimilarityMeasureIndefinite2010]. In particular, we gave a higher weight to suggestions with a higher rank, with weights decaying by a factor of $k^{0.80}$. @fig-simulations-rbo shows how the average agreement with the baseline scales, which take the top 256 tags from each server.
|
||||
|
||||
:::
|
||||
|
||||
# Discussion
|
||||
|
||||
The analysis can also be improved by additionally focusing on factors lead to accounts remaining active or dropping out, which a particular focus on the actual activity of accounts over time. For instance, do accounts that interact with other users more remain active longer? Are there particular markers of activity that are more predictive of account retention? Future work could use these to provide suggests for ways to helps newcomers during the onboarding process.
|
||||
|
||||
The observational nature of the data limit some of the causal claims we can make. It is unclear, for instance, if accounts on general servers are less likely to remain active because of the server itself or because of the type of users who join such servers. For example, it is conceivable that the kind of person who spends more time researching which server to join is more invested in their Mastodon experience than one who simply joins the first server they find.
|
||||
|
||||
Future work is necessary to determine the how well the recommendation system is at helping users find servers that match their interests. This may involve user studies and interviews to determine how well the system works in practice.
|
||||
|
||||
While the work presented here is based on observed posts on the public timelines, simulations may be helpful in determining the robustness of the system to targeted attacks. Due to the decentralized nature of the system, it is feasible that a bad actor could set up zombie accounts on servers to manipulate the recommendation system. Simulations could help determine how well the system can resist such attacks and ways to mitigate this risk.
|
||||
|
||||
# Conclusion
|
||||
|
||||
Based on analysis of trace data from millions of new Fediverse accounts, we find evidence that suggests that servers matter and that users tend to move from larger servers to smaller servers. We then propose a recommendation system that can help new Fediverse users find servers with a high probability of being a good match based on their interests. Based on simulations, we demonstrate that such a tool can be effectively deployed in a federated manner, even with limited data on each local server.
|
||||
|
||||
# References {#references}
|
||||
|
||||
::: {.content-visible unless-profile="icwsm"}
|
||||
|
||||
# Glossary {.appendix}
|
||||
|
||||
*ActivityPub*: A decentralized social networking protocol based on the ActivityStreams 2.0 data format.
|
||||
|
||||
*Fediverse*: A set of decentralized online social networks which interoperate using shared protocols like ActivityPub.
|
||||
|
||||
*Mastodon*: An open-source, decentralized social network and microblogging community.
|
||||
|
||||
*Hashtag*: A user-generated metadata tag that can be added to posts.
|
||||
|
||||
*Federated timeline*: A timeline which includes all posts from users followed by other users on their server.
|
||||
|
||||
*Local timeline*: A timeline with all public posts from the local server.
|
||||
:::
|
||||
|
||||
::: {.content-visible when-format="html"}
|
||||
|
||||
```{r}
|
||||
library(tidyverse)
|
||||
library(arrow)
|
||||
library(ggrepel)
|
||||
|
||||
"data/scratch/server_svd.feather" %>% arrow::read_ipc_file() %>%
|
||||
as_tibble %>%
|
||||
ggplot(aes(x = x, y = y, label = server)) +
|
||||
geom_text_repel(size = 2, max.overlaps = 10) +
|
||||
#geom_point() +
|
||||
theme_minimal()
|
||||
```
|
||||
|
||||
```{r}
|
||||
library(tidyverse)
|
||||
library(arrow)
|
||||
library(ggrepel)
|
||||
library(here)
|
||||
library(jsonlite)
|
||||
|
||||
top_tags <- "data/scratch/tag_svd.feather" %>% arrow::read_ipc_file() %>%
|
||||
as_tibble %>%
|
||||
mutate(s = variance * log(count)) %>% arrange(desc(s))
|
||||
|
||||
top_tags %>%
|
||||
select(tag, index) %>%
|
||||
jsonlite::write_json(here("recommender/data/top_tags.json"))
|
||||
|
||||
top_tags %>%
|
||||
head(100) %>%
|
||||
ggplot(aes(x = x, y = y, label = tag)) +
|
||||
geom_text_repel(size = 3, max.overlaps = 10) +
|
||||
#geom_point() +
|
||||
theme_minimal()
|
||||
```
|
||||
|
||||
:::
|
||||
32
notebooks/revisions.qmd
Normal file
32
notebooks/revisions.qmd
Normal file
@ -0,0 +1,32 @@
|
||||
---
|
||||
title: Revisions and Response
|
||||
author: Carl Colglazier
|
||||
---
|
||||
|
||||
Provide background for the recommendation system
|
||||
|
||||
> - Identify key examples of the kinds of systems/features the one you have proposed/created aligns with.
|
||||
>
|
||||
> - Situate your approach in relation to key prior work that motivates the approach you pursue
|
||||
|
||||
I added two sections to the background section of the text which describe recommender systems/collaborative filtering and trade-offs in different methods of evaluation. This system connects with prior work from HCI researchers, e.g. in the GroupLens lab, to build discovery and recommender systems.
|
||||
|
||||
## Elaborate the design rationale for the system in the text.
|
||||
|
||||
> - Why recommend small/specific servers?
|
||||
>
|
||||
> - What key related work justifies the approach you pursue to designing the system in the way you do?
|
||||
|
||||
In addition to the previous survivor models, I added a logistic regression model based on a continuous measure of server "generality" to support the decision to steer newcomers toward more topic-based and smaller servers. Future work can look at specific users to see if engagement with hashtags and local timelines is indicative of better retention.
|
||||
|
||||
TODO: key related work
|
||||
|
||||
## Address system evaluation more directly in the paper
|
||||
|
||||
> - Explain, justify, and interpret the evaluation that is present in the paper
|
||||
>
|
||||
> - Elaborate/justify additional system evaluation plans (e.g., usability; robustness to dropping servers/tags; balancing tradeoffs; navigating privacy/trust/safety concerns)
|
||||
|
||||
## Clearly identify the research/design contributions of this system
|
||||
|
||||
> - Both at present and assuming your proposed development plans move forward
|
||||
423
presentations/aijc.qmd
Normal file
423
presentations/aijc.qmd
Normal file
@ -0,0 +1,423 @@
|
||||
---
|
||||
title: "Do Servers Matter on Mastodon?"
|
||||
subtitle: "Data-driven Design for Recommendations in Decentralized Social Media"
|
||||
author: "Carl Colglazier"
|
||||
institute:
|
||||
- "Community Data Science Collective"
|
||||
- "Northwestern University"
|
||||
date: "2024-05-13"
|
||||
bibliography: ../references.bib
|
||||
title-slide-attributes:
|
||||
data-background: "#4c3854"
|
||||
format:
|
||||
revealjs:
|
||||
width: 1600
|
||||
height: 900
|
||||
date-format: long
|
||||
margin: 0.2
|
||||
center-title-slide: false
|
||||
#disable-layout: true
|
||||
theme: [default, presentation.scss]
|
||||
slide-number: false
|
||||
keep-md: true
|
||||
pdf-max-pages-per-slide: 1
|
||||
template-partials:
|
||||
- title-slide.html
|
||||
# beamer:
|
||||
# aspectratio: 169
|
||||
# theme: metropolis
|
||||
# colortheme: seahorse
|
||||
knitr:
|
||||
opts_chunk:
|
||||
dev: "ragg_png"
|
||||
retina: 1
|
||||
dpi: 300
|
||||
execute:
|
||||
freeze: auto
|
||||
cache: true
|
||||
echo: false
|
||||
# fig-width: 5
|
||||
# fig-height: 6
|
||||
prefer-html: true
|
||||
---
|
||||
|
||||
# Outline
|
||||
|
||||
+ Motivating a recommender system for Mastodon servers
|
||||
|
||||
+ High level overview of recommender systems
|
||||
|
||||
+ Demo?
|
||||
|
||||
|
||||
# The Big Picture {.center}
|
||||
|
||||
What is decentralized social media and why does it matter?
|
||||
|
||||
|
||||
|
||||
## Emergance of the Social Web
|
||||
|
||||
:::::: {.spread}
|
||||
|
||||
Internet technologies are _sociotechnical_ systems.
|
||||
|
||||
The social internet as we know it today emerged both from the develeopment of **protocols** and systems [@abbateInventingInternet2000] and thousands of largely non-commercial **social communities** [@driscollModemWorldPrehistory2022].
|
||||
|
||||
:::: {.columns}
|
||||
::: {.column width=33%}
|
||||
:::: {.fragment fragment-index=1}
|
||||
#### Era
|
||||
::::
|
||||
:::: {.fragment fragment-index=2}
|
||||
ARPANET
|
||||
::::
|
||||
:::: {.fragment fragment-index=3}
|
||||
Early Internet
|
||||
::::
|
||||
:::: {.fragment fragment-index=4}
|
||||
Commercial Web
|
||||
::::
|
||||
:::
|
||||
::: {.column width=33%}
|
||||
:::: {.fragment fragment-index=1}
|
||||
#### Spaces
|
||||
::::
|
||||
:::: {.fragment fragment-index=2}
|
||||
Email, Usenet
|
||||
::::
|
||||
:::: {.fragment fragment-index=3}
|
||||
BBS, IRC
|
||||
::::
|
||||
:::: {.fragment fragment-index=4}
|
||||
Social media
|
||||
::::
|
||||
:::
|
||||
::: {.column width=33%}
|
||||
:::: {.fragment fragment-index=1}
|
||||
#### Technologies
|
||||
::::
|
||||
:::: {.fragment fragment-index=2}
|
||||
TCP/IP
|
||||
::::
|
||||
:::: {.fragment fragment-index=3}
|
||||
HTML
|
||||
::::
|
||||
:::: {.fragment fragment-index=4}
|
||||
APIs, AJAX
|
||||
::::
|
||||
:::
|
||||
:::
|
||||
|
||||
::::::
|
||||
|
||||
## Current Trends
|
||||
|
||||
::: {}
|
||||
|
||||
+ High **distrust** of social media companies [@AmericansWidelyDistrust2021]
|
||||
|
||||
+ Challenges in performing content moderation and maintaining social communities at **scale** [@gillespieContentModerationAI2020]
|
||||
|
||||
+ Post-API Era: **closure** of APIs on major platforms to researchers and tinkerers [@freelonComputationalResearchPostAPI2018]
|
||||
|
||||
## Protocol-based Social Media
|
||||
|
||||
::::: {.spread}
|
||||
|
||||
The commercial internet has trended toward centralization, but this may be neither desirable nor sustainable [@masnickProtocolsNotPlatforms].
|
||||
|
||||
::: {.columns}
|
||||
::: {.column}
|
||||
#### Platforms
|
||||
|
||||
We have accounts on the same website
|
||||
:::
|
||||
::: {.column}
|
||||
#### Protocols
|
||||
|
||||
We use the same protocol
|
||||
:::
|
||||
:::
|
||||
|
||||
|
||||
::: {.columns}
|
||||
::: {.column}
|
||||
The (single) website controls:
|
||||
|
||||
- My data
|
||||
|
||||
- Content moderation
|
||||
|
||||
- Monetization
|
||||
:::
|
||||
::: {.column}
|
||||
I can choose who controls:
|
||||
|
||||
- My data
|
||||
|
||||
- Content moderation (local)
|
||||
|
||||
- Monetization (if any)
|
||||
:::
|
||||
:::
|
||||
|
||||
:::::
|
||||
|
||||
|
||||
|
||||
## Empirical Context
|
||||
|
||||
::: {.columns}
|
||||
|
||||
:::: {.column}
|
||||
|
||||
- **The Fediverse**: A set of decentralized online social networks which interoperate using shared protocols like ActivityPub.
|
||||
|
||||
- **Mastodon**: An open-source, decentralized social network and microblogging community.
|
||||
|
||||
::::
|
||||
|
||||
:::: {.column}
|
||||
|
||||
|
||||
|
||||
::::
|
||||
|
||||
:::
|
||||
|
||||
# The Fediverse is a network of _thousands_ of interconnected servers {background-color="black" data-background-image="images/mastodon_map.png" background-repeat="repeat" background-size="200px" background-opacity="0.5" .center auto-animate=true .fade-out}
|
||||
|
||||
## Mastodon grew significantly in 2022 and 2023
|
||||
|
||||
```{r}
|
||||
#| label: fig-account-timeline
|
||||
#| fig-width: 5
|
||||
#| fig-height: 2.5
|
||||
library(here)
|
||||
source(here("code/helpers.R"))
|
||||
account_timeline_plot()
|
||||
```
|
||||
|
||||
## Which server should I join?
|
||||
|
||||
### Conflicting advice
|
||||
|
||||
::: {.columns}
|
||||
::: {.column}
|
||||
|
||||
Just join any server!
|
||||
|
||||
:::
|
||||
::: {.column}
|
||||
|
||||
Join the _right_ server!
|
||||
|
||||
:::
|
||||
:::
|
||||
|
||||
::: {.fragment}
|
||||
### Which is right? {.center-xy}
|
||||
:::
|
||||
|
||||
---
|
||||
|
||||
{.center}
|
||||
|
||||
# Does server choice matter? {.center}
|
||||
|
||||
## Survival model for new accounts
|
||||
|
||||
Are they more likely to stay active after 91 days.
|
||||
|
||||
::: {.columns}
|
||||
|
||||
::: {.column}
|
||||
|
||||
```{r, cache.extra = tools::md5sum("code/survival.R")}
|
||||
#| cache: true
|
||||
#| label: fig-survival
|
||||
#| fig-env: figure
|
||||
#| fig-cap: "Survival probabilities for accounts created during May 2023."
|
||||
#| fig-width: 3.375
|
||||
#| fig-height: 2.25
|
||||
#| fig-pos: h!
|
||||
|
||||
library(here)
|
||||
source(here("code/survival.R"))
|
||||
plot_km
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
::: {.column .small}
|
||||
|
||||
```{r}
|
||||
#| label: tbl-coxme
|
||||
library(ehahelper)
|
||||
library(broom)
|
||||
|
||||
cxme_table <- tidy(cxme) %>%
|
||||
mutate(conf.low = exp(conf.low), conf.high=exp(conf.high)) %>%
|
||||
mutate(term = case_when(
|
||||
term == "factor(group)1" ~ "Join Mastodon",
|
||||
term == "factor(group)2" ~ "General Servers",
|
||||
term == "small_serverTRUE" ~ "Small Server",
|
||||
TRUE ~ term
|
||||
)) %>%
|
||||
mutate(exp.coef = paste("(", round(conf.low, 2), ", ", round(conf.high, 2), ")", sep="")) %>%
|
||||
select(term, estimate, exp.coef , p.value)
|
||||
|
||||
cxme_table %>% knitr::kable(digits = 3)
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
:::
|
||||
|
||||
## Accounts that move
|
||||
|
||||
Do they move to larger servers or to smaller servers?
|
||||
|
||||
::: {.small}
|
||||
|
||||
```{r}
|
||||
#| label: tbl-ergm-table
|
||||
#| echo: false
|
||||
#| warning: false
|
||||
#| message: false
|
||||
#| error: false
|
||||
|
||||
library(here)
|
||||
library(modelsummary)
|
||||
library(kableExtra)
|
||||
library(purrr)
|
||||
library(stringr)
|
||||
load(file = here("data/scratch/ergm-model-early.rda"))
|
||||
load(file = here("data/scratch/ergm-model-late.rda"))
|
||||
|
||||
if (knitr::is_latex_output()) {
|
||||
format <- "latex_tabular"
|
||||
} else {
|
||||
format <- "html"
|
||||
}
|
||||
|
||||
x <- modelsummary(
|
||||
list("Coef." = model.early, "Std.Error" = model.early, "Coef." = model.late, "Std.Error" = model.late),
|
||||
estimate = c("{estimate}", "{stars}{std.error}", "{estimate}", "{stars}{std.error}"),
|
||||
statistic = NULL,
|
||||
gof_omit = ".*",
|
||||
coef_rename = c(
|
||||
"sum" = "Sum",
|
||||
"nonzero" = "Nonzero",
|
||||
"diff.sum0.h-t.accounts" = "Smaller server",
|
||||
"nodeocov.sum.accounts" = "Server size\n(outgoing)",
|
||||
"nodeifactor.sum.registrations.TRUE" = "Open registrations\n(incoming)",
|
||||
"nodematch.sum.language" = "Languages match"
|
||||
),
|
||||
align="lrrrr",
|
||||
stars = c('*' = .05, '**' = 0.01, '***' = .001),
|
||||
output = format
|
||||
) %>% add_header_above(c(" " = 1, "Model A" = 2, "Model B" = 2))
|
||||
|
||||
x
|
||||
```
|
||||
|
||||
:::
|
||||
|
||||
# Our analysis suggests {.center}
|
||||
|
||||
- Accounts on large, general servers fare worse
|
||||
- Moved accounts go to smaller servers
|
||||
|
||||
Can we build a system that helps people find servers?
|
||||
|
||||
# Recommender Systems
|
||||
|
||||
What is a recommender system?
|
||||
|
||||
## Approaches: Collaborative Filtering
|
||||
|
||||
- **User-based**: Recommend items liked by similar users
|
||||
|
||||
- **Item-based**: Recommend items similar to those liked by the user
|
||||
|
||||
## Approaches: Deep Learning
|
||||
|
||||
Good at finding weird trends and signals.
|
||||
|
||||
How do they work? Why do they suggest what they do?
|
||||
|
||||
🤷
|
||||
|
||||
## Approaches: Latent Factor Based
|
||||
|
||||
|
||||
+ Latent semantic analysis (LSA), singular value decomposition (SVD), latent Dirichlet allocation (LDA)
|
||||
|
||||
## Challenges: Cold Start Problem
|
||||
|
||||
+ **New communities**: We don't have enough data on anything
|
||||
|
||||
+ **New users**: We don't know enough about them to make good recommendations
|
||||
|
||||
+ **New items**: Not enough people have tried them
|
||||
|
||||
## Challenges: The Harry Potter Effect
|
||||
|
||||
Popular items get more ratings.
|
||||
|
||||
But these items aren't really the most interesting.
|
||||
|
||||
# My Recommender System Concept
|
||||
|
||||
- Report top **hashtags** used by the most accounts on each server
|
||||
- Build an $M \times N$ server-tag matrix
|
||||
- Normalize with Okai BM25 TF-IDF and L2 normalization
|
||||
|
||||
|
||||
::: {.fragment}
|
||||
Using this matrix, we can
|
||||
|
||||
- Calculate similarity between servers using tags
|
||||
- Calculate similarity between tags using servers
|
||||
- Reccommend servers based on affinity toward certain tags
|
||||
:::
|
||||
|
||||
## Example: Server Similarity
|
||||
|
||||
::: {#tbl-sim-servers}
|
||||
|
||||
```{r}
|
||||
#| label: table-sim-servers
|
||||
library(tidyverse)
|
||||
library(arrow)
|
||||
library(here)
|
||||
|
||||
sim_servers <- here("data/scratch/server_similarity.feather") %>% arrow::read_ipc_file()
|
||||
server_of_interest <- "hci.social"
|
||||
server_table <- sim_servers %>%
|
||||
arrange(desc(Similarity)) %>%
|
||||
filter(Source == server_of_interest | Target == server_of_interest) %>%
|
||||
head(7) %>%
|
||||
pivot_longer(cols=c(Source, Target)) %>%
|
||||
filter(value != server_of_interest) %>%
|
||||
select(value, Similarity) %>%
|
||||
rename("Server" = "value")
|
||||
|
||||
if (knitr::is_latex_output()) {
|
||||
server_table %>% knitr::kable(format="latex", booktabs=TRUE, digits=3)
|
||||
} else {
|
||||
server_table %>% knitr::kable(digits = 3)
|
||||
}
|
||||
```
|
||||
|
||||
Top five servers most similar to hci.social
|
||||
|
||||
:::
|
||||
|
||||
# Future Work
|
||||
|
||||
- Evaluation of the recommendation system
|
||||
- More specific analysis of account attributes
|
||||
- Simulations for robustness
|
||||
202
references.bib
202
references.bib
@ -53,6 +53,36 @@
|
||||
isbn = {978-1-60558-246-7}
|
||||
}
|
||||
|
||||
@article{bushWeMayThink1945,
|
||||
title = {As {{We May Think}}},
|
||||
author = {Bush, Vannevar},
|
||||
year = {1945},
|
||||
month = jul,
|
||||
journal = {The Atlantic},
|
||||
volume = {176},
|
||||
number = {1},
|
||||
pages = {101--108},
|
||||
urldate = {2020-03-04},
|
||||
abstract = {``Consider a future device {\dots}~~in which an individual stores all his books, records, and communications, and which is mechanized so that it may be consulted with exceeding speed and flexibility. It is an enlarged intimate supplement to his memory.''},
|
||||
langid = {american}
|
||||
}
|
||||
|
||||
@inproceedings{cosleySuggestBotUsingIntelligent2007,
|
||||
title = {{{SuggestBot}}: {{Using Intelligent Task Routing}} to {{Help People Find Work}} in {{Wikipedia}}},
|
||||
shorttitle = {{{SuggestBot}}},
|
||||
booktitle = {Proceedings of the 12th {{International Conference}} on {{Intelligent User Interfaces}}},
|
||||
author = {Cosley, Dan and Frankowski, Dan and Terveen, Loren and Riedl, John},
|
||||
year = {2007},
|
||||
series = {{{IUI}} '07},
|
||||
pages = {32--41},
|
||||
publisher = {ACM},
|
||||
address = {New York, NY, USA},
|
||||
doi = {10.1145/1216295.1216309},
|
||||
urldate = {2016-05-23},
|
||||
abstract = {Member-maintained communities ask their users to perform tasks the community needs. From Slashdot, to IMDb, to Wikipedia, groups with diverse interests create community-maintained artifacts of lasting value (CALV) that support the group's main purpose and provide value to others. Said communities don't help members find work to do, or do so without regard to individual preferences, such as Slashdot assigning meta-moderation randomly. Yet social science theory suggests that reducing the cost and increasing the personal value of contribution would motivate members to participate more.We present SuggestBot, software that performs intelligent task routing (matching people with tasks) in Wikipedia. SuggestBot uses broadly applicable strategies of text analysis, collaborative filtering, and hyperlink following to recommend tasks. SuggestBot's intelligent task routing increases the number of edits by roughly four times compared to suggesting random articles. Our contributions are: 1) demonstrating the value of intelligent task routing in a real deployment; 2) showing how to do intelligent task routing; and 3) sharing our experience of deploying a tool in Wikipedia, which offered both challenges and opportunities for research.},
|
||||
isbn = {978-1-59593-481-9}
|
||||
}
|
||||
|
||||
@misc{diazUsingMastodonWay2022,
|
||||
title = {Using {{Mastodon}} Is Way Too Complicated to Ever Topple {{Twitter}}},
|
||||
author = {Diaz, Jesus},
|
||||
@ -89,6 +119,23 @@
|
||||
langid = {american}
|
||||
}
|
||||
|
||||
@article{ekstrandCollaborativeFilteringRecommender2011,
|
||||
title = {Collaborative {{Filtering Recommender Systems}}},
|
||||
author = {Ekstrand, Michael D. and Riedl, John T. and Konstan, Joseph A.},
|
||||
year = {2011},
|
||||
month = may,
|
||||
journal = {Foundations and Trends{\textregistered} in Human--Computer Interaction},
|
||||
volume = {4},
|
||||
number = {2},
|
||||
pages = {81--173},
|
||||
publisher = {Now Publishers, Inc.},
|
||||
issn = {1551-3955, 1551-3963},
|
||||
doi = {10.1561/1100000009},
|
||||
urldate = {2024-05-21},
|
||||
abstract = {Collaborative Filtering Recommender Systems},
|
||||
langid = {english}
|
||||
}
|
||||
|
||||
@article{fieslerMovingLandsOnline2020,
|
||||
title = {Moving across Lands: Online Platform Migration in Fandom Communities},
|
||||
shorttitle = {Moving across Lands},
|
||||
@ -156,6 +203,39 @@
|
||||
keywords = {machine learning,mastodon,topic modeling,twitter,user migration}
|
||||
}
|
||||
|
||||
@article{herlockerEvaluatingCollaborativeFiltering2004,
|
||||
title = {Evaluating Collaborative Filtering Recommender Systems},
|
||||
author = {Herlocker, Jonathan L. and Konstan, Joseph A. and Terveen, Loren G. and Riedl, John T.},
|
||||
year = {2004},
|
||||
month = jan,
|
||||
journal = {ACM Transactions on Information Systems},
|
||||
volume = {22},
|
||||
number = {1},
|
||||
pages = {5--53},
|
||||
issn = {1046-8188},
|
||||
doi = {10.1145/963770.963772},
|
||||
urldate = {2020-08-06},
|
||||
abstract = {Recommender systems have been evaluated in many, often incomparable, ways. In this article, we review the key decisions in evaluating collaborative filtering recommender systems: the user tasks being evaluated, the types of analysis and datasets being used, the ways in which prediction quality is measured, the evaluation of prediction attributes other than quality, and the user-based evaluation of the system as a whole. In addition to reviewing the evaluation strategies used by prior researchers, we present empirical results from the analysis of various accuracy metrics on one content domain where all the tested metrics collapsed roughly into three equivalence classes. Metrics within each equivalency class were strongly correlated, while metrics from different equivalency classes were uncorrelated.},
|
||||
keywords = {Collaborative filtering,evaluation,metrics,recommender systems}
|
||||
}
|
||||
|
||||
@inproceedings{herlockerExplainingCollaborativeFiltering2000,
|
||||
title = {Explaining Collaborative Filtering Recommendations},
|
||||
booktitle = {Proceedings of the 2000 {{ACM}} Conference on {{Computer}} Supported Cooperative Work},
|
||||
author = {Herlocker, Jonathan L. and Konstan, Joseph A. and Riedl, John},
|
||||
year = {2000},
|
||||
month = dec,
|
||||
series = {{{CSCW}} '00},
|
||||
pages = {241--250},
|
||||
publisher = {Association for Computing Machinery},
|
||||
address = {New York, NY, USA},
|
||||
doi = {10.1145/358916.358995},
|
||||
urldate = {2020-08-05},
|
||||
abstract = {Automated collaborative filtering (ACF) systems predict a person's affinity for items or information by connecting that person's recorded interests with the recorded interests of a community of people and sharing ratings between like-minded persons. However, current recommender systems are black boxes, providing no transparency into the working of the recommendation. Explanations provide that transparency, exposing the reasoning and data behind a recommendation. In this paper, we address explanation interfaces for ACF systems - how they should be implemented and why they should be implemented. To explore how, we present a model for explanations based on the user's conceptual model of the recommendation process. We then present experimental results demonstrating what components of an explanation are the most compelling. To address why, we present experimental evidence that shows that providing explanations can improve the acceptance of ACF systems. We also describe some initial explorations into measuring how explanations can improve the filtering performance of users.},
|
||||
isbn = {978-1-58113-222-9},
|
||||
keywords = {collaborative filtering,explanations,GroupLens,MoviesLens,recommender systems}
|
||||
}
|
||||
|
||||
@article{hooverMastodonBumpNow2023,
|
||||
title = {The {{Mastodon Bump Is Now}} a {{Slump}}},
|
||||
author = {Hoover, Amanda},
|
||||
@ -252,6 +332,23 @@
|
||||
langid = {english}
|
||||
}
|
||||
|
||||
@inproceedings{lamAddressingColdstartProblem2008,
|
||||
title = {Addressing Cold-Start Problem in Recommendation Systems},
|
||||
booktitle = {Proceedings of the 2nd International Conference on {{Ubiquitous}} Information Management and Communication},
|
||||
author = {Lam, Xuan Nhat and Vu, Thuc and Le, Trong Duc and Duong, Anh Duc},
|
||||
year = {2008},
|
||||
month = jan,
|
||||
series = {{{ICUIMC}} '08},
|
||||
pages = {208--211},
|
||||
publisher = {Association for Computing Machinery},
|
||||
address = {New York, NY, USA},
|
||||
doi = {10.1145/1352793.1352837},
|
||||
urldate = {2024-05-21},
|
||||
abstract = {Recommender systems for automatically suggested items of interest to users have become increasingly essential in fields where mass personalization is highly valued. The popular core techniques of such systems are collaborative filtering, content-based filtering and combinations of these. In this paper, we discuss hybrid approaches, using collaborative and also content data to address cold-start - that is, giving recommendations to novel users who have no preference on any items, or recommending items that no user of the community has seen yet. While there have been lots of studies on solving the item-side problems, solution for user-side problems has not been seen public. So we develop a hybrid model based on the analysis of two probabilistic aspect models using pure collaborative filtering to combine with users' information. The experiments with MovieLen data indicate substantial and consistent improvements of this model in overcoming the cold-start user-side problem.},
|
||||
isbn = {978-1-59593-993-7},
|
||||
keywords = {aspect model,cold-start,collaborative filtering,information filtering,three-way aspect model,triadic aspect model}
|
||||
}
|
||||
|
||||
@misc{masnickProtocolsNotPlatforms,
|
||||
title = {Protocols, {{Not Platforms}}: {{A Technological Approach}} to {{Free Speech}}},
|
||||
shorttitle = {Protocols, {{Not Platforms}}},
|
||||
@ -301,6 +398,16 @@
|
||||
keywords = {community rules,Mastodon,online communities}
|
||||
}
|
||||
|
||||
@article{paterekImprovingRegularizedSingular2007,
|
||||
title = {Improving Regularized Singular Value Decomposition for Collaborative Filtering},
|
||||
author = {Paterek, Arkadiusz},
|
||||
year = {2007},
|
||||
month = aug,
|
||||
journal = {Proceedings of KDD cup and workshop},
|
||||
abstract = {A key part of a recommender system is a collaborative filtering algorithm predicting users' preferences for items. In this paper we describe different efficient collaborative filtering techniques and a framework for combining them to obtain a good prediction.},
|
||||
langid = {english}
|
||||
}
|
||||
|
||||
@inproceedings{ramanChallengesDecentralisedWeb2019a,
|
||||
title = {Challenges in the {{Decentralised Web}}: {{The Mastodon Case}}},
|
||||
shorttitle = {Challenges in the {{Decentralised Web}}},
|
||||
@ -318,6 +425,22 @@
|
||||
isbn = {978-1-4503-6948-0}
|
||||
}
|
||||
|
||||
@inproceedings{resnickGrouplensOpenArchitecture1994,
|
||||
title = {Grouplens: An Open Architecture for Collaborative Filtering of Netnews},
|
||||
shorttitle = {Grouplens},
|
||||
booktitle = {Proceedings of the 1994 {{ACM Conference}} on {{Computer Supported Cooperative Work}}},
|
||||
author = {Resnick, Paul and Iacovou, Neophytos and Suchak, Mitesh and Bergstrom, Peter and Riedl, John},
|
||||
year = {1994},
|
||||
series = {{{CSCW}} '94},
|
||||
pages = {175--186},
|
||||
publisher = {ACM},
|
||||
address = {New York, NY, USA},
|
||||
doi = {10.1145/192844.192905},
|
||||
urldate = {2016-07-19},
|
||||
abstract = {Collaborative filters help people make choices based on the opinions of other people. GroupLens is a system for collaborative filtering of netnews, to help people find articles they will like in the huge stream of available articles. News reader clients display predicted scores and make it easy for users to rate articles after they read them. Rating servers, called Better Bit Bureaus, gather and disseminate the ratings. The rating servers predict scores based on the heuristic that people who agreed in the past will probably agree again. Users can protect their privacy by entering ratings under pseudonyms, without reducing the effectiveness of the score prediction. The entire architecture is open: alternative software for news clients and Better Bit Bureaus can be developed independently and can interoperate with the components we have developed.},
|
||||
isbn = {978-0-89791-689-9}
|
||||
}
|
||||
|
||||
@book{ricciRecommenderSystemsHandbook2022,
|
||||
title = {Recommender Systems Handbook},
|
||||
editor = {Ricci, Francesco and Ro{\d k}a{\d h}, Liʾor and Shapira, Bracha},
|
||||
@ -330,6 +453,22 @@
|
||||
langid = {english}
|
||||
}
|
||||
|
||||
@article{robertsonProbabilisticRelevanceFramework2009,
|
||||
title = {The {{Probabilistic Relevance Framework}}: {{BM25}} and {{Beyond}}},
|
||||
shorttitle = {The {{Probabilistic Relevance Framework}}},
|
||||
author = {Robertson, Stephen and Zaragoza, Hugo},
|
||||
year = {2009},
|
||||
journal = {Foundations and Trends{\textregistered} in Information Retrieval},
|
||||
volume = {3},
|
||||
number = {4},
|
||||
pages = {333--389},
|
||||
issn = {1554-0669, 1554-0677},
|
||||
doi = {10.1561/1500000019},
|
||||
urldate = {2024-05-20},
|
||||
abstract = {The Probabilistic Relevance Framework (PRF) is a formal framework for document retrieval, grounded in work done in the 1970--1980s, which led to the development of one of the most successful text-retrieval algorithms, BM25. In recent years, research in the PRF has yielded new retrieval models capable of taking into account document meta-data (especially structure and link-graph information). Again, this has led to one of the most successful Web-search and corporate-search algorithms, BM25F. This work presents the PRF from a conceptual point of view, describing the probabilistic modelling assumptions behind the framework and the different ranking algorithms that result from its application: the binary independence model, relevance feedback models, BM25 and BM25F. It also discusses the relation between the PRF and other statistical models for IR, and covers some related topics, such as the use of non-textual features, and parameter optimisation for models with free parameters.},
|
||||
langid = {english}
|
||||
}
|
||||
|
||||
@misc{rochkoMastodon2023,
|
||||
title = {Mastodon 4.2},
|
||||
author = {Rochko, Eugen},
|
||||
@ -364,6 +503,18 @@
|
||||
langid = {english}
|
||||
}
|
||||
|
||||
@book{saltonIntroductionModernInformation1987,
|
||||
title = {Introduction to Modern Information Retrieval},
|
||||
author = {Salton, Gerard and McGill, Michael J.},
|
||||
year = {1987},
|
||||
series = {{{McGraw-Hill}} International Editions},
|
||||
edition = {3. pr},
|
||||
publisher = {McGraw-Hill Book Comp},
|
||||
address = {New York},
|
||||
isbn = {978-0-07-054484-0},
|
||||
langid = {english}
|
||||
}
|
||||
|
||||
@inproceedings{sarwarItembasedCollaborativeFiltering2001,
|
||||
title = {Item-Based Collaborative Filtering Recommendation Algorithms},
|
||||
booktitle = {Proceedings of the 10th International Conference on {{World Wide Web}}},
|
||||
@ -379,6 +530,24 @@
|
||||
isbn = {978-1-58113-348-6}
|
||||
}
|
||||
|
||||
@incollection{schaferCollaborativeFilteringRecommender2007,
|
||||
title = {Collaborative Filtering Recommender Systems},
|
||||
booktitle = {The {{Adaptive Web}}: {{Methods}} and {{Strategies}} of {{Web Personalization}}},
|
||||
author = {Schafer, J. Ben and Frankowski, Dan and Herlocker, Jon and Sen, Shilad},
|
||||
editor = {Brusilovsky, Peter and Kobsa, Alfred and Nejdl, Wolfgang},
|
||||
year = {2007},
|
||||
series = {Lecture {{Notes}} in {{Computer Science}}},
|
||||
pages = {291--324},
|
||||
publisher = {Springer},
|
||||
address = {Berlin, Heidelberg},
|
||||
doi = {10.1007/978-3-540-72079-9_9},
|
||||
urldate = {2020-08-06},
|
||||
abstract = {One of the potent personalization technologies powering the adaptive web is collaborative filtering. Collaborative filtering (CF) is the process of filtering or evaluating items through the opinions of other people. CF technology brings together the opinions of large interconnected communities on the web, supporting filtering of substantial quantities of data. In this chapter we introduce the core concepts of collaborative filtering, its primary uses for users of the adaptive web, the theory and practice of CF algorithms, and design decisions regarding rating systems and acquisition of ratings. We also discuss how to evaluate CF systems, and the evolution of rich interaction interfaces. We close the chapter with discussions of the challenges of privacy particular to a CF recommendation service and important open research questions in the field.},
|
||||
isbn = {978-3-540-72079-9},
|
||||
langid = {english},
|
||||
keywords = {Association Rule Mining,Collaborative Filter,Explicit Rating,News Article,Recommender System}
|
||||
}
|
||||
|
||||
@misc{silberlingBeginnerGuideMastodon2023,
|
||||
title = {A Beginner's Guide to {{Mastodon}}, the Open Source {{Twitter}} Alternative {\textbar} {{TechCrunch}}},
|
||||
author = {Silberling, Amanda},
|
||||
@ -389,6 +558,22 @@
|
||||
howpublished = {https://techcrunch.com/2023/07/24/what-is-mastodon/}
|
||||
}
|
||||
|
||||
@article{suSurveyCollaborativeFiltering2009,
|
||||
title = {A {{Survey}} of {{Collaborative Filtering Techniques}}},
|
||||
author = {Su, Xiaoyuan and Khoshgoftaar, Taghi M.},
|
||||
year = {2009},
|
||||
month = oct,
|
||||
journal = {Advances in Artificial Intelligence},
|
||||
volume = {2009},
|
||||
pages = {e421425},
|
||||
publisher = {Hindawi},
|
||||
issn = {1687-7470},
|
||||
doi = {10.1155/2009/421425},
|
||||
urldate = {2024-05-09},
|
||||
abstract = {As one of the most successful approaches to building recommender systems, collaborative filtering (CF) uses the known preferences of a group of users to make recommendations or predictions of the unknown preferences for other users. In this paper, we first introduce CF tasks and their main challenges, such as data sparsity, scalability, synonymy, gray sheep, shilling attacks, privacy protection, etc., and their possible solutions. We then present three main categories of CF techniques: memory-based, model-based, and hybrid CF algorithms (that combine CF with other recommendation techniques), with examples for representative algorithms of each category, and analysis of their predictive performance and their ability to address the challenges. From basic techniques to the state-of-the-art, we attempt to present a comprehensive survey for CF techniques, which can be served as a roadmap for research and practice in this area.},
|
||||
langid = {english}
|
||||
}
|
||||
|
||||
@inproceedings{teblunthuisIdentifyingCompetitionMutualism2022,
|
||||
title = {Identifying Competition and Mutualism between Online Groups},
|
||||
booktitle = {International {{AAAI Conference}} on {{Web}} and {{Social Media}} ({{ICWSM}} 2022)},
|
||||
@ -463,6 +648,23 @@
|
||||
keywords = {FEVR,Framework for EValuating Recommender systems,Survey}
|
||||
}
|
||||
|
||||
@inproceedings{zhuPopularityOpportunityBiasCollaborative2021,
|
||||
title = {Popularity-{{Opportunity Bias}} in {{Collaborative Filtering}}},
|
||||
booktitle = {Proceedings of the 14th {{ACM International Conference}} on {{Web Search}} and {{Data Mining}}},
|
||||
author = {Zhu, Ziwei and He, Yun and Zhao, Xing and Zhang, Yin and Wang, Jianling and Caverlee, James},
|
||||
year = {2021},
|
||||
month = mar,
|
||||
series = {{{WSDM}} '21},
|
||||
pages = {85--93},
|
||||
publisher = {Association for Computing Machinery},
|
||||
address = {New York, NY, USA},
|
||||
doi = {10.1145/3437963.3441820},
|
||||
urldate = {2024-05-21},
|
||||
abstract = {This paper connects equal opportunity to popularity bias in implicit recommenders to introduce the problem of popularity-opportunity bias. That is, conditioned on user preferences that a user likes both items, the more popular item is more likely to be recommended (or ranked higher) to the user than the less popular one. This type of bias is harmful, exerting negative effects on the engagement of both users and item providers. Thus, we conduct a three-part study: (i) By a comprehensive empirical study, we identify the existence of the popularity-opportunity bias in fundamental matrix factorization models on four datasets; (ii) coupled with this empirical study, our theoretical study shows that matrix factorization models inherently produce the bias; and (iii) we demonstrate the potential of alleviating this bias by both in-processing and post-processing algorithms. Extensive experiments on four datasets show the effective debiasing performance of these proposed methods compared with baselines designed for conventional popularity bias.},
|
||||
isbn = {978-1-4503-8297-7},
|
||||
keywords = {equal opportunity,recommendation bias,recommender systems,statistical parity}
|
||||
}
|
||||
|
||||
@article{zulliRethinkingSocialSocial2020,
|
||||
title = {Rethinking the ``Social'' in ``Social Media'': {{Insights}} into Topology, Abstraction, and Scale on the {{Mastodon}} Social Network},
|
||||
shorttitle = {Rethinking the ``Social'' in ``Social Media''},
|
||||
|
||||
145
template.tex
145
template.tex
@ -1,145 +0,0 @@
|
||||
\documentclass[letterpaper]{article} % DO NOT CHANGE THIS
|
||||
\usepackage[submission]{aaai24} % DO NOT CHANGE THIS
|
||||
\usepackage{times} % DO NOT CHANGE THIS
|
||||
\usepackage{helvet} % DO NOT CHANGE THIS
|
||||
\usepackage{courier} % DO NOT CHANGE THIS
|
||||
\usepackage[hyphens]{url} % DO NOT CHANGE THIS
|
||||
\usepackage{graphicx} % DO NOT CHANGE THIS
|
||||
\urlstyle{rm} % DO NOT CHANGE THIS
|
||||
\def\UrlFont{\rm} % DO NOT CHANGE THIS
|
||||
\usepackage{natbib} % DO NOT CHANGE THIS AND DO NOT ADD ANY OPTIONS TO IT
|
||||
\usepackage{caption} % DO NOT CHANGE THIS AND DO NOT ADD ANY OPTIONS TO IT
|
||||
\frenchspacing % DO NOT CHANGE THIS
|
||||
\setlength{\pdfpagewidth}{8.5in} % DO NOT CHANGE THIS
|
||||
\setlength{\pdfpageheight}{11in} % DO NOT CHANGE THIS
|
||||
|
||||
\usepackage{amsmath}
|
||||
\usepackage{amssymb}
|
||||
\usepackage{booktabs}
|
||||
\usepackage{siunitx}
|
||||
%
|
||||
% These are recommended to typeset algorithms but not required. See the subsubsection on algorithms. Remove them if you don't have algorithms in your paper.
|
||||
%\usepackage{algorithm}
|
||||
%\usepackage{algorithmic}
|
||||
|
||||
%
|
||||
% These are are recommended to typeset listings but not required. See the subsubsection on listing. Remove this block if you don't have listings in your paper.
|
||||
%\usepackage{newfloat}
|
||||
%\usepackage{listings}
|
||||
%\DeclareCaptionStyle{ruled}{labelfont=normalfont,labelsep=colon,strut=off} % DO NOT CHANGE THIS
|
||||
%\lstset{%
|
||||
% basicstyle={\footnotesize\ttfamily},% footnotesize acceptable for monospace
|
||||
% numbers=left,numberstyle=\footnotesize,xleftmargin=2em,% show line numbers, remove this entire line if you don't want the numbers.
|
||||
% aboveskip=0pt,belowskip=0pt,%
|
||||
% showstringspaces=false,tabsize=2,breaklines=true}
|
||||
%\floatstyle{ruled}
|
||||
%\newfloat{listing}{tb}{lst}{}
|
||||
%\floatname{listing}{Listing}
|
||||
%
|
||||
% Keep the \pdfinfo as shown here. There's no need
|
||||
% for you to add the /Title and /Author tags.
|
||||
\pdfinfo{
|
||||
/TemplateVersion (2024.1)
|
||||
}
|
||||
|
||||
% DISALLOWED PACKAGES
|
||||
% \usepackage{authblk} -- This package is specifically forbidden
|
||||
% \usepackage{balance} -- This package is specifically forbidden
|
||||
% \usepackage{color (if used in text)
|
||||
% \usepackage{CJK} -- This package is specifically forbidden
|
||||
% \usepackage{float} -- This package is specifically forbidden
|
||||
% \usepackage{flushend} -- This package is specifically forbidden
|
||||
% \usepackage{fontenc} -- This package is specifically forbidden
|
||||
% \usepackage{fullpage} -- This package is specifically forbidden
|
||||
% \usepackage{geometry} -- This package is specifically forbidden
|
||||
% \usepackage{grffile} -- This package is specifically forbidden
|
||||
% \usepackage{hyperref} -- This package is specifically forbidden
|
||||
% \usepackage{navigator} -- This package is specifically forbidden
|
||||
% (or any other package that embeds links such as navigator or hyperref)
|
||||
% \indentfirst} -- This package is specifically forbidden
|
||||
% \layout} -- This package is specifically forbidden
|
||||
% \multicol} -- This package is specifically forbidden
|
||||
% \nameref} -- This package is specifically forbidden
|
||||
% \usepackage{savetrees} -- This package is specifically forbidden
|
||||
% \usepackage{setspace} -- This package is specifically forbidden
|
||||
% \usepackage{stfloats} -- This package is specifically forbidden
|
||||
% \usepackage{tabu} -- This package is specifically forbidden
|
||||
% \usepackage{titlesec} -- This package is specifically forbidden
|
||||
% \usepackage{tocbibind} -- This package is specifically forbidden
|
||||
% \usepackage{ulem} -- This package is specifically forbidden
|
||||
% \usepackage{wrapfig} -- This package is specifically forbidden
|
||||
% DISALLOWED COMMANDS
|
||||
% \nocopyright -- Your paper will not be published if you use this command
|
||||
% \addtolength -- This command may not be used
|
||||
% \balance -- This command may not be used
|
||||
% \baselinestretch -- Your paper will not be published if you use this command
|
||||
% \clearpage -- No page breaks of any kind may be used for the final version of your paper
|
||||
% \columnsep -- This command may not be used
|
||||
% \newpage -- No page breaks of any kind may be used for the final version of your paper
|
||||
% \pagebreak -- No page breaks of any kind may be used for the final version of your paperr
|
||||
% \pagestyle -- This command may not be used
|
||||
% \tiny -- This is not an acceptable font size.
|
||||
% \vspace{- -- No negative value may be used in proximity of a caption, figure, table, section, subsection, subsubsection, or reference
|
||||
% \vskip{- -- No negative value may be used to alter spacing above or below a caption, figure, table, section, subsection, subsubsection, or reference
|
||||
|
||||
\setcounter{secnumdepth}{0} %May be changed to 1 or 2 if section numbers are desired.
|
||||
\newcolumntype{d}{S[
|
||||
input-open-uncertainty=,
|
||||
input-close-uncertainty=,
|
||||
parse-numbers = false,
|
||||
table-align-text-pre=false,
|
||||
table-align-text-post=false
|
||||
]}
|
||||
|
||||
|
||||
\def\tightlist{}
|
||||
\def\phantomsection{}
|
||||
\newcommand\hypertarget[2]{#2}
|
||||
\newcommand\texorpdfstring[2]{#1}
|
||||
\newcommand\bookmarksetup[1]{}
|
||||
\newcommand\href[1]{#1}
|
||||
|
||||
\usepackage{longtable}
|
||||
%\renewenvironment{longtable}{\begin{center}\begin{tabular}}{\end{tabular}\end{center}}
|
||||
%\def\endhead{}
|
||||
%\renewcommand{\toprule}[2]{\hline}
|
||||
%\renewcommand{\midrule}[2]{\hline}
|
||||
%renewcommand{\bottomrule}[2]{\hline}
|
||||
% long table two column hack
|
||||
\makeatletter
|
||||
\let\oldlt\longtable
|
||||
\let\endoldlt\endlongtable
|
||||
\def\longtable{\@ifnextchar[\longtable@i \longtable@ii}
|
||||
\def\longtable@i[#1]{\begin{figure}[htbp]
|
||||
\begin{minipage}{0.5\textwidth}
|
||||
\onecolumn
|
||||
\oldlt[#1]
|
||||
}
|
||||
\def\longtable@ii{\begin{figure}[htbp]
|
||||
\begin{minipage}{0.5\textwidth}
|
||||
\onecolumn
|
||||
\oldlt
|
||||
}
|
||||
\def\endlongtable{\endoldlt
|
||||
\end{minipage}
|
||||
\twocolumn
|
||||
\end{figure}}
|
||||
\makeatother
|
||||
|
||||
\title{$title$}
|
||||
|
||||
\begin{document}
|
||||
|
||||
\maketitle
|
||||
|
||||
$if(abstract)$
|
||||
\begin{abstract}
|
||||
$abstract$
|
||||
\end{abstract}
|
||||
$endif$
|
||||
|
||||
$body$
|
||||
|
||||
\bibliography{$bibliography$}
|
||||
|
||||
\end{document}
|
||||
Loading…
Reference in New Issue
Block a user