Contextual semantics for sentiment analysis of Twitter

作者：

Highlights：

•

• We propose a semantic sentiment representation of words called SentiCircle.

• SentiCircle captures the contextual semantic of words from their co-occurrences.

• SentiCircle updates the sentiment of words based on their contextual semantics.

• SentiCircle can be used to perform entity- and tweet-level level sentiment analysis.

摘要

•We propose a semantic sentiment representation of words called SentiCircle.•SentiCircle captures the contextual semantic of words from their co-occurrences.•SentiCircle updates the sentiment of words based on their contextual semantics.•SentiCircle can be used to perform entity- and tweet-level level sentiment analysis.

论文关键词：Sentiment analysis,Contextual semantics,Twitter

论文评审过程：Received 30 April 2014, Revised 24 November 2014, Accepted 28 January 2015, Available online 7 March 2015, Version of Record 10 December 2015.

论文官网地址：https://doi.org/10.1016/j.ipm.2015.01.005