Are Web User Comments Useful for Search

Abstract

the potential impact of comments on search accuracy in social Web sites. We characterize YouTube comments, showing that they have the potential to distinguish videos. Furthermore, we show how they could be incorporated into the index, yielding up to a 15% increase in search accu racy. a video returned the corresponding video. If content is poorly described by the title/descrip tion/keywords, however, comment information may supplement or replace traditional forms of search. The title/description /keywords of a Westminster Kennel Show video, for example, may fail to mention (not to mention particular breeds ), and thus not turn up in the results for dog show. Searchin g through comment information will almost certainly solve thi s problem. In this paper, we explore the nature of user comm ents and how they may aid in search. Specifically, we analyze t he term distributions of user comments and attempt to apply this information to improve search accuracy. The hazard associated with the use of comments to i mprove search accuracy is that they may contain noisy term s that hurt performance as well as significantly increase the s ize of the index. Our experimental results, however, suggest that whi le some queries are negatively affected by comments, overal l, they can improve query accuracy by nearly 15%. Furthermore, we apply techniques that can reduce the cost of using commen ts by up to 70%.