学术报告:Serendipitous Recommendation: Especially for Scholarly Papers and Mobile Apps

时间:2016.11.29(周二) 16:30-18:30

地点:研究所106会议室

[Title] :"Serendipitous Recommendation: Especially for Scholarly Papers and Mobile Apps"

[Abstract]

Recommendation engines are particularly well-suited for the task of serendipitous recommendation, in comparison to the standard search engine, as they do not need to fulfill specific targeted query. In the domain of scholarly papers, if serendipitous recommendations are realized, junior researchers can employ them to broaden their horizon and learn about new areas, while senior researchers can discover interdisciplinary frontiers to apply integrative research. We adapt the user profile construction procedure in a state-of-the-art scholarly paper recommendation system to make use of information drawn from (1) dissimilar users and (2) co-authors to specifically target serendipitous recommendation.

On the other hand, in the domain of mobile applications (apps), existing recommender systems merely recommend apps that users have experienced (rated, commented, or downloaded) since this type of information indicates each user's preference for the apps. Unfortunately, this prunes the apps which are releavnt but are not featured in the recommendation lists since users have never experienced them. Motivated by this phenomenon, our work proposes a method for recommending serendipitous apps using graph-based techniques.

[Biography]

Kazunari Sugiyama is a research fellow at National University of Singapore from April, 2009. He is a visiting scholar at Pennsylvania State University from January to May, 2014.

He received his B.Eng and M.Eng degrees from Yokohama National University, Japan, in 1998 and 2000, respectively. In 2004, he also received his Ph.D. degree from Nara Institute of Science and Technology, Japan, He then worked

for Hitachi, Ltd., Software Division, Japan, from 2004 to 2006. After that, he was a research fellow at Tokyo Institute of Technology, Japan, from 2006 to 2009.

His research interests include information retrieval, digital libraries (especially on recommendation systems) and natural language processing (especially on personal name disambiguation in Web search results and word sense disambiguation in Japanese texts). He is a winner of "Vannevar Bush Best Paper Award" at JCDL'13.

[关闭]
版权所有 © 2007 北京大学计算机科学技术研究所