Latent Social Networks and Communities An Empirical Analysis of LONCAPA User Data.pdfVIP

Latent Social Networks and Communities: An Empirical Analysis of LON-CAPA User Data 1 1 2 Peng Han , Bernd Kr¨amer , and Gerd Kortemeyer 1 FernUniversit¨at of Hagen, Hagen 54084, Germany {han.peng, bernd.kraemer}@fernuni-hagen.de 2 Michigan State University, MI 48823, USA kortemey@ Summary. the emergence and increasing popularity of social software like BBS, Blog, Wiki and Podcasting, the concept of community has shown its important role in the design and implementation of the next generation of web applications. In this paper, we report on an empirical study we performed to discover communities of practice among LON-CAPA users by analyzing log data collected over a period of three years. LON-CAPA is one of the leading online learning content manage- ment and assessment systems. We identified several kinds of social communities and showed how they may possibly influence people’s selection on learning resources. Finally, we conclude our contribution and describe the future work 1 Introduction The World Wide Web (WWW) has become one of the most comprehensive and popular forums to share knowledge and digital resources. Various online systems have been developed ranging from learning object repositories and peer-reviewed link collections like LON-CAPA 3 , MERLOT 4 and Connexion5 to research paper index services such as DBLP6 and Cite seer7 . While providing users with unprecedented abundant information, the ever increasing amount of resources also inevitably brings about the problem of information overload [7]. As a result, the question ”How to evaluate the relevance and quality of candidate resources according to a specific search scenario?” has gained increasing attention both in academia and industry. Keyword based search is currently the dominant approach employed