Opinion polarity detection in Twitter data combining shrinkage regression and topic modeling

作者：

Highlights：

• A method for analyzing public opinion online by detecting polarity in Twitter data.

• The method uses regression techniques and topic modeling.

• The method showed high polarity detection accuracy for the mayoral selection in Seoul, Korea.

摘要

•A method for analyzing public opinion online by detecting polarity in Twitter data.•The method uses regression techniques and topic modeling.•The method showed high polarity detection accuracy for the mayoral selection in Seoul, Korea.

论文关键词：Sentiment analysis,Shrinkage regression,Topic modeling

论文评审过程：Received 23 July 2015, Revised 30 March 2016, Accepted 30 March 2016, Available online 9 May 2016, Version of Record 9 May 2016.

论文官网地址：https://doi.org/10.1016/j.joi.2016.03.006