CatIss: An Intelligent Tool for Categorizing Issues Reports using Transformers

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

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 report, Enhancement/feature request, and Question. 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. 1
Original languageEnglish
Title of host publicationProceedings of the 2022 IEEE/ACM 1st International Workshop on Natural Language-Based Software Engineering (NLBSE)
PublisherIEEE
Pages44-47
Number of pages4
ISBN (Electronic)978-1-4503-9343-0
ISBN (Print)978-1-6654-6231-0
Publication statusPublished - 2022
Event2022 IEEE/ACM 1st International Workshop on Natural Language-Based Software Engineering (NLBSE) - Pittsburgh, United States
Duration: 8 May 20228 May 2022

Workshop

Workshop2022 IEEE/ACM 1st International Workshop on Natural Language-Based Software Engineering (NLBSE)
Country/TerritoryUnited States
CityPittsburgh
Period8/05/228/05/22

Keywords

  • Issue report Management
  • Classification, Repositories
  • Transformers
  • Machine Learning
  • Natural Language Processing

Fingerprint

Dive into the research topics of 'CatIss: An Intelligent Tool for Categorizing Issues Reports using Transformers'. Together they form a unique fingerprint.

Cite this