Followee recommendation based on text analysis of micro-blogging activity

作者：

Highlights：

• We present an effective algorithm for recommending followees in Twitter.

• We defined four different strategies to create content-based user profiles.

• The target user's own tweets are not a good source of profiling knowledge.

• Profiles based on the posts of the target user's followees give high precision values.

摘要

Highlights•We present an effective algorithm for recommending followees in Twitter.•We defined four different strategies to create content-based user profiles.•The target user's own tweets are not a good source of profiling knowledge.•Profiles based on the posts of the target user's followees give high precision values.

论文关键词：Micro-blogging,Text mining,Recommender systems

论文评审过程：Received 12 August 2011, Revised 3 May 2013, Accepted 29 May 2013, Available online 5 June 2013.

论文官网地址：https://doi.org/10.1016/j.is.2013.05.009