Analysis of sentiment in tweets addressed to a single domain-specific Twitter account: Comparison of model performance and explainability of predictions

作者：

Highlights：

• Comparison of selected popular and recent natural language processing methods.

• Use of explainable Artificial Intelligence tools in Twitter sentiment analysis.

• Analysis of sentiment in tweets addressed to a single Twitter account.

• Performance of selected transformer models on the SemEval-2017 data set.

摘要

•Comparison of selected popular and recent natural language processing methods.•Use of explainable Artificial Intelligence tools in Twitter sentiment analysis.•Analysis of sentiment in tweets addressed to a single Twitter account.•Performance of selected transformer models on the SemEval-2017 data set.

论文关键词：Natural language processing,Deep learning,Sentiment analysis,Machine learning,Explainability,Twitter

论文评审过程：Received 8 July 2020, Revised 12 August 2021, Accepted 12 August 2021, Available online 21 August 2021, Version of Record 4 September 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115771