Title :
Evaluation of Session-Based Recommendation Systems for Social Networks
Author :
Chen-Ling Chen ; Chia-Hui Chang
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Central Univ., Jhongli, Taiwan
Abstract :
Tencent Weibo is one of the largest micro-blogging websites in China. There are more than 200 million registered users on Tencent Weibo, generating over 40 million messages each day. Recommending appealing items to users is a mechanism to reduce the risk of information overload. The task of this paper is to predict whether or not a user will follow an item that has been recommended to the user by Tencent Weibo. This paper contains two parts: predicting users´ interests and distinguish whether the user is busy or available to browse recommended items. We apply several model based collaborative filtering as well as content-based filtering to capture users´ interests. Besides, we built an occupied model to distinguish users´ state and combined with recommendations methods as the final result. In the paper, we used session-based hamming loss as performance measure. The hamming loss of recommendation methods were greatly reduced (40%) with occupied model from 0.187 to 0.13.
Keywords :
collaborative filtering; recommender systems; social networking (online); Tencent Weibo; content-based filtering; information overload risk reduction; item recommendation; microblogging Web sites; model based collaborative filtering; performance measure; session-based hamming loss; session-based recommendation systems; social networks; user interests prediction; Collaboration; Filtering; Matrix decomposition; Predictive models; Testing; Training; Training data; collaborative filtering; matrix factorization; social network recommendation;
Conference_Titel :
Data Mining Workshops (ICDMW), 2013 IEEE 13th International Conference on
Conference_Location :
Dallas, TX
Print_ISBN :
978-1-4799-3143-9
DOI :
10.1109/ICDMW.2013.86
