Mining affective text to improve social media item recommendation

作者：

Highlights：

• We propose a sentiment-aware social media recommendation framework.

• An ensemble learning-based method is proposed to classify sentiments from affective texts.

• We conduct comprehensive experiments to verify the effectiveness of the proposed methods.

摘要

•We propose a sentiment-aware social media recommendation framework.•An ensemble learning-based method is proposed to classify sentiments from affective texts.•We conduct comprehensive experiments to verify the effectiveness of the proposed methods.

论文关键词：Social media,Recommender system,Sentiment classification,OCCF

论文评审过程：Received 15 August 2013, Revised 1 June 2014, Accepted 18 September 2014, Available online 27 October 2014, Version of Record 6 June 2015.

论文官网地址：https://doi.org/10.1016/j.ipm.2014.09.002