A domain transferable lexicon set for Twitter sentiment analysis using a supervised machine learning approach

作者：

Highlights：

• A domain transferable, Twitter specific lexicon for sentiment analysis is proposed.

• The approach produces more accurate results than competing lexicons.

• Five datasets are used to show domain transferability with excellent results.

摘要

•A domain transferable, Twitter specific lexicon for sentiment analysis is proposed.•The approach produces more accurate results than competing lexicons.•Five datasets are used to show domain transferability with excellent results.

论文关键词：Twitter sentiment analysis,Domain transferability,n-gram analysis,Machine learning,Dynamic artificial neural networks (DAN2)

论文评审过程：Received 23 May 2017, Revised 4 April 2018, Accepted 4 April 2018, Available online 7 April 2018, Version of Record 16 April 2018.

论文官网地址：https://doi.org/10.1016/j.eswa.2018.04.006