Title: A comprehensive survey on aspect-based sentiment analysis

Authors: Kaustubh Yadav; Neeraj Kumar; Praveen Kumar Reddy Maddikunta; Thippa Reddy Gadekallu

Addresses: School of Computer Science and Engineering, Vellore Institute of Technology, Tamil Nadu, India ' Department of Computer Science and Engineering, Thapar Institute of Engineering and Technology, Patiala (Pb.), India ' School of Information Technology and Engineering, Vellore Institute of Technology, Tamil Nadu, India ' School of Information Technology and Engineering, Vellore Institute of Technology, Tamil Nadu, India

Abstract: Aspect-based sentiment analysis (ABSA) is the sub-field of natural language processing that deals with breaking or splitting texts into aspects and then classification into sentiments like happy, sad, angry, etc. towards the aspect. Aspect-based sentiment analysis provides more information about the context than general sentiment analysis. In this survey paper, we compared a variety of papers and the methods that were introduced through them on achieving better results for the problem at hand. As ABSA is currently being used for customer satisfaction and product feedback most of the papers have datasets containing reviews. This survey paper discusses various solutions in-depth and gives a comparison between them. Firstly, we discuss rule-based approaches and then move to complex approaches that involve both rule-based approaches and neural networks. Also, major emphasis is shed on the principles and the workflow of the method discussed.

Keywords: aspect-based sentiment analysis? ABSA? neural networks? rule-based approach? machine learning? naive Bayes.

DOI: 10.1504/IJESMS.2021.10043476

International Journal of Engineering Systems Modelling and Simulation, 2021 Vol.12 No.4, pp.279 - 290

Received: 30 Jun 2020
Accepted: 13 Nov 2020

Published online: 22 Dec 2021 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article