32 lines
1.6 KiB
Plaintext
32 lines
1.6 KiB
Plaintext
---
|
|
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 |