Approaches to Cross-Domain Sentiment Analysis: A Systematic Literature Review

Abstract

A sentiment analysis has received a lot of attention from researchers working in the fields of natural language processing and text mining. However, there is a lack of annotated data sets that can be used to train a model for all domains, which is hampering the accuracy of sentiment analysis. Many research studies have attempted to tackle this issue and to improve cross-domain sentiment classification. In this paper, we present the results of a comprehensive systematic literature review of the methods and techniques employed in a cross-domain sentiment analysis. We focus on studies published during the period of 2010–2016. From our analysis of those works, it is clear that there is no perfect solution. Hence, one of the aims of this review is to create a resource in the form of an overview of the techniques, methods, and approaches that have been used to attempt to solve the problem of cross-domain sentiment analysis in order to assist researchers in developing new and more accurate techniques in the future.