Unsupervised method for sentiment analysis in online texts

作者：

Highlights：

• Method to predict sentiment in informal texts using unsupervised dependency parsing.

• Algorithm based on sentiment propagation using linguistic content without training.

• Method to create lexicon using polarity expansion algorithm for specific domains.

• Our method compares favorably well with other unsupervised and supervised methods.

摘要

•Method to predict sentiment in informal texts using unsupervised dependency parsing.•Algorithm based on sentiment propagation using linguistic content without training.•Method to create lexicon using polarity expansion algorithm for specific domains.•Our method compares favorably well with other unsupervised and supervised methods.

论文关键词：Sentiment analysis,Opinion mining,nlp,Artificial intelligence,68Q55,68T50

论文评审过程：Received 26 October 2015, Revised 17 March 2016, Accepted 18 March 2016, Available online 1 April 2016, Version of Record 13 April 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.03.031