Is ChatGPT a Good Sentiment Analyzer? A Preliminary Study

TL;DR

This study preliminarily evaluates ChatGPT's ability to analyze opinions, sentiments, and emotions across multiple sentiment analysis tasks, comparing it with fine-tuned models and exploring prompting techniques.

Contribution

It provides a comprehensive evaluation of ChatGPT's sentiment analysis performance across diverse tasks and datasets, highlighting its strengths and limitations.

Findings

ChatGPT performs competitively on several sentiment analysis tasks.

Prompting techniques can enhance ChatGPT's sentiment understanding.

Human evaluation reveals nuanced insights into ChatGPT's capabilities.

Abstract

Recently, ChatGPT has drawn great attention from both the research community and the public. We are particularly interested in whether it can serve as a universal sentiment analyzer. To this end, in this work, we provide a preliminary evaluation of ChatGPT on the understanding of \emph{opinions}, \emph{sentiments}, and \emph{emotions} contained in the text. Specifically, we evaluate it in three settings, including \emph{standard} evaluation, \emph{polarity shift} evaluation and \emph{open-domain} evaluation. We conduct an evaluation on 7 representative sentiment analysis tasks covering 17 benchmark datasets and compare ChatGPT with fine-tuned BERT and corresponding state-of-the-art (SOTA) models on them. We also attempt several popular prompting techniques to elicit the ability further. Moreover, we conduct human evaluation and present some qualitative case studies to gain a deep comprehension of its sentiment analysis capabilities.