Our research group at the University of Michigan has been working on the "related modules" block for Drupal.org for more than 2 years now. We have published 2 papers on this project so far:
1) Assessment of Conversation Co-mentions as a Resource for Software Module Recommendation. Will be presented at ACM Recommender System Conference'09
2) Conversation Pivots and Double Pivots. Presented at ACM Computer Human Interaction Conference'08
Thanks to the support of Google Summer of Code'09, I was able to develop the Recommender Bundle for Drupal, which includes the following modules:
http://drupal.org/project/recommender
http://drupal.org/project/history_rec
http://drupal.org/project/fivestar_rec
http://drupal.org/project/voting_rec
http://drupal.org/project/uc_rec
http://drupal.org/project/similargroups
http://drupal.org/project/media_rec (not developed)
My Google Summer of Code 2009 proposal was accepted. The basic idea is to develop at least three modules based on Recommender API. For example, one module is to recommend Flash videos based on users' viewing history like in YouTube. A mockup screenshot is like this:
For more details and discussion, please go to http://groups.drupal.org/node/19894.
There's a big demand from the Drupal community to add fivestar-like ratings to the contrib modules. This would be a pretty cool feature, but it has other concerns too.
A brief history to begin with ...
The idea is to generate "related modules" recommendation based on co-citations. Suppose we have TinyMCE and FCKeditor co-mentioned together in many forum discussions, then we consider the 2 modules related to some extend. Here is a detailed explanation.
From the experience of developing the "pivots" Drupal module recommendation system, I developed the general purpose Recommender API module. It was released today.
Previously, 'related modules' were generated based on discussions in d.o. forum -- if several modules were mentioned in the same discussion threads, we consider them to be somewhat related. (More detailed explanation of the algorithms can be found in my previous Planet Drupal blogs).
From the last Google Analytics (GA) study on the usefulness of "pivots_block" on 4 recommendation algorithms, we learned that the classical "relevancy" algorithm generated the better results. Therefore, we used the relevancy algorithm on D.O. from Dec/4/2008 to Jan/9/2009. And the average click-thru rate was 0.474%.
We developed 4 module recommendation algorithms and tested them on Drupal.org. And we used Google Analytics and tracked the click-through rates. The overall click-through rate was 0.263%, co-occurrences 0.097%, relevance 0.141%, recency 0.114% and uniqueness 0.138%. The relevancy algorithm appeared to have the highest click-through rate, but it was only significantly higher than the co-occurrences algorithm.
You might have noticed that the pivots_block is enabled on drupal.org module pages, such as http://drupal.org/project/i18n. This blog is trying to explain the algorithms we are using in the pivots recommendation system.
