Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review

• Published in: Expert systems with applications 2019-03, Vol.118, p.272-299
• Main Authors: Do, Hai Ha, Prasad, PWC, Maag, Angelika, Alsadoon, Abeer
• Format: Article
• Language: English
• Subjects: Classification; Cognition & reasoning; Data mining; Deep learning; Expert systems; Learning; Neural networks; Sentiment analysis; User generated content
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2018.10.003

•Over 40 models for aspect-based sentiment analysis are summarized and classified.•Deep learning methods use fewer parameters but achieved comparative performance.•Deep learning is still in infancy, given challenges in data, domains and languages.•A task-combined and concept-centric approach should be considered in future studies. The increasing volume of user-generated content on the web has made sentiment analysis an important tool for the extraction of information about the human emotional state. A current research focus for sentiment analysis is the improvement of granularity at aspect level, representing two distinct aims: aspect extraction and sentiment classification of product reviews and sentiment classification of target-dependent tweets. Deep learning approaches have emerged as a prospect for achieving these aims with their ability to capture both syntactic and semantic features of text without requirements for high-level feature engineering, as is the case in earlier methods. In this article, we aim to provide a comparative review of deep learning for aspect-based sentiment analysis to place different approaches in context.