Sentiment Analysis Using Dialogue Data: A Taxonomy of Literature

Abstract

In a rapidly advancing world of artificial intelligence and natural language processing, the need to understand human dialogue with information systems is ever more pressing. This paper presents a taxonomy of sentiment analysis using dialogue data, developed via a scoping literature review and employment of a widely recognized taxonomy method. By synthesizing the diverse approaches across 18 papers (comprising 22 dimensions and 328 categories), we present a framework that highlights the components underpinning current work, including application domains, data characteristics, sentiment analysis pipelines, methods and dialogue-specific information utilized. By offering a detailed, method-focused view of the existing research, our taxonomy aims to guide future studies that seek to integrate sentiment analysis into dialogue systems. We discuss issues in the current state of the literature and conclude by providing directions for future research.