Paper Reading #20: Supporting Exploratory Information Seeking by Epistemology-based Social Search

Comments

Reference information
Author: Yuqing Mao, Haifeng Shen, Chengzheng Chen
When/Where: IUI '10, February 7–10, 2010, Hong Kong, China

Summary
This paper discusses Baijia, a system to improve upon conventional search engines like Google and Yahoo using epistemological social searching, which reuses and redefines other users' contributions, allowing users to share web searches.Baijia allows users submit a query and select search pages for it, which are then added to the epistemology. Other users can subscribe to, rank and comment on these search pages to improve them; related queries can then be presented to the first user.

For evaluation, the designers selected AOL query logs as a baseline, comparing them to Baijia's search results. The system showed better performance than AOL, as it re-ranks search results according to users’ judgments.

Discussion
The evaluation section seemed lacking in explanation and detail. I think the problem of formulating proper keywords or search queries is there but is not very prevalent, thus I do not believe the problem or solution are very important. I also struggled for some time understanding EIS and what an epistemology was. Still, I think there is potential in this kind of application. I do witness some of my friends, some computer science majors, entering whole questions as search queries, so this can still be helpful. The social aspect of the application was pretty interesting and actually seems useful; I probably wouldn't have thought of implementing that if I were part of the design team.