CatIss: An Intelligent Tool for Categorizing Issues Reports using Transformers

TL;DR

CatIss is a Transformer-based tool that automatically categorizes issue reports into bugs, feature requests, or questions, demonstrating high accuracy and broad applicability across software projects.

Contribution

This paper introduces CatIss, a novel Transformer-based issue report categorizer that outperforms existing baselines and is adaptable to unseen projects.

Findings

Achieved 87.2% F1-score on GitHub issue reports.

Surpassed baseline models like TicketTagger.

Demonstrated effectiveness across diverse repositories.

Abstract

Users use Issue Tracking Systems to keep track and manage issue reports in their repositories. An issue is a rich source of software information that contains different reports including a problem, a request for new features, or merely a question about the software product. As the number of these issues increases, it becomes harder to manage them manually. Thus, automatic approaches are proposed to help facilitate the management of issue reports. This paper describes CatIss, an automatic CATegorizer of ISSue reports which is built upon the Transformer-based pre-trained RoBERTa model. CatIss classifies issue reports into three main categories of Bug reports, Enhancement/feature requests, and Questions. First, the datasets provided for the NLBSE tool competition are cleaned and preprocessed. Then, the pre-trained RoBERTa model is fine-tuned on the preprocessed dataset. Evaluating CatIss on about 80 thousand issue reports from GitHub, indicates that it performs very well surpassing the competition baseline, TicketTagger, and achieving 87.2% F1-score (micro average). Additionally, as CatIss is trained on a wide set of repositories, it is a generic prediction model, hence applicable for any unseen software project or projects with little historical data. Scripts for cleaning the datasets, training CatIss, and evaluating the model are publicly available.