Professor Jae-Gil Lee, Assistant Professor from the Department of Knowledge Service Engineering at KAIST, won the Best Paper Award at the 7th International Conference on Weblogs and Social Media (ICWSM) sponsored by the Association for the Advancement of Artificial Intelligence (AAAI). This conference, hosted at Massachusetts Institute of Technology (MIT), aims to bring together researchers from computer and social sciences in order to enhance the understanding of social media and its technological successors.

The paper, titled “Booming Up the Long Tails: Discovering Potentially Contributive Users in Community-based Question Answering Services,” explores the methodology of identifying expert contributors to community-based question answering (CQA) services by analyzing the vocabulary in the users’ answers.

A CQA is a knowledge sharing service where users are able to submit questions and answer existing questions posted by other users. This type of service relies chiefly upon the how many and how frequent users provide reliable information. In practice, many questions are answered by a select few “expert” users, and the quality of a particular CQA service relies disproportionately on these users.

Using ten years’ worth of raw data from Korea’s leading CQA service Naver Knowledge-In (KIN), Professor Lee proposed an analytical model that accurately selects potential expert users who had only recently joined the service. This research topic is expected to be further developed into a commercial service through cooperative research with major Internet corporations.

Professor Lee received his bachelor’s, master’s, and doctor’s degrees from KAIST’s Department of Computer Science. He previously worked as a post-doctoral researcher at IBM Almaden Research Center, and as a post-doctoral research associate at the University of Illinois Urbana-Champaign’s Department of Computer Science. His fields of interests include spatio-temporal data mining and recommender systems.