User Follow Prediction of Microblog Based on the Activeness and Interest Similarity

CAO Yunzhong, SHAO Peiji, LI Liangqiang, ZHOU Kairui

Abstract


Many microblog fans have formed the basis of microblog information dissemination and diffusion, so accurate prediction and attracting more potential customers to follow microblogger becomes very necessary. By employing interpersonal relationship network of microblog fans, this study integrates microblogger popularity and user activeness into interest similarity in order to explain user follow predictor and propose user follow prediction models. Support vector machine (SVM) is used to train this model. Open data from Tencent microblog in KDD Cup 2012 prove that the proposed prediction model has higher prediction accuracy and stability.
Key words: Microblog; User follow; Microblogger popularity; User activeness; Interest similarity; Prediction model

Keywords


Microblog; User follow; Microblogger popularity; User activeness; Interest similarity; Prediction model

Full Text:

PDF


DOI: http://dx.doi.org/10.3968%2Fj.ibm.1923842820130701.1100

Refbacks

  • There are currently no refbacks.


Reminder

If you have already registered in Journal A and plan to submit article(s) to Journal B, please click the CATEGORIES, or JOURNALS A-Z on the right side of the "HOME".


We only use three mailboxes as follows to deal with issues about paper acceptance, payment and submission of electronic versions of our journals to databases: caooc@hotmail.com; ibm@cscanada.net; ibm@cscanada.org

Copyright © 2010 Canadian Research & Development Centre of Sciences and Cultures
Address: 758, 77e AV, Laval, Quebec, H7V 4A8, Canada

Telephone: 1-514-558 6138
Http://www.cscanada.net
Http://www.cscanada.org
E-mail:caooc@hotmail.com