This work aims at creating a user recommender system that recommends relevant people to follow for twitter users. We propose to use a novel topic modeling method Biterm Topic Model (BTM) to profile users into vectors of bag of words. We then propose an algorithm that uses both social network relationship information and the user-generated content modeled through BTM to recommend twitter followees. A preliminary evaluation is carried out on the implementation of this technique that shows BTM performs well in making valid recommendations to twitter users. We also found that considering both user generated content and social relationships for recommending followees helped improve the results.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com