Exploring Zero-Shot App Review Classification with ChatGPT: Challenges and Potential

TL;DR

This paper investigates the use of ChatGPT's zero-shot learning capabilities to classify app reviews into functional and non-functional categories, achieving high accuracy without domain-specific training data.

Contribution

It demonstrates that ChatGPT can effectively classify app reviews into multiple categories using zero-shot learning, reducing the need for costly labeled datasets.

Findings

ChatGPT achieves an F1 score of 0.842 in review classification.

Review readability and length influence classification accuracy.

Certain review categories are more prone to misclassification.

Abstract

App reviews are a critical source of user feedback, offering valuable insights into an app's performance, features, usability, and overall user experience. Effectively analyzing these reviews is essential for guiding app development, prioritizing feature updates, and enhancing user satisfaction. Classifying reviews into functional and non-functional requirements play a pivotal role in distinguishing feedback related to specific app features (functional requirements) from feedback concerning broader quality attributes, such as performance, usability, and reliability (non-functional requirements). Both categories are integral to informed development decisions. Traditional approaches to classifying app reviews are hindered by the need for large, domain-specific datasets, which are often costly and time-consuming to curate. This study explores the potential of zero-shot learning with ChatGPT for classifying app reviews into four categories: functional requirement, non-functional requirement, both, or neither. We evaluate ChatGPT's performance on a benchmark dataset of 1,880 manually annotated reviews from ten diverse apps spanning multiple domains. Our findings demonstrate that ChatGPT achieves a robust F1 score of 0.842 in review classification, despite certain challenges and limitations. Additionally, we examine how factors such as review readability and length impact classification accuracy and conduct a manual analysis to identify review categories more prone to misclassification.