QuME tackles the expertise location and maintenance problem for large-scale Q&A communities. It does so by automatically distributing tasks to people who have the necessary expertise.Expertise finders are an important class of collaborative recommendation systems, but they suffer from a general problem: Current expertise finders, both commercial and research, cannot infer expertise levels very well. QuME includes novel algorithm to infer expertise levels, making a larger range of social interaction possible.
The SocialWorlds Research group has conducted numerous studies of Q&A communities. Our interest has been in how these communities function. The first study was of Java Forum, and it detailed how the community functioned and how expertise was distributed and shared. We then studied Yahoo Answers, along with its sister sites Naver in Korea and Baidu in China. We also compared the three sites. These studies examined why answerer helped, and whether there were intercultural differences.