"BERT-Based GitHub Issue Report Classification" accepted at NLBSE 2022 (co-located with ICSE'22).

"BERT-Based GitHub Issue Report Classification" accepted at NLBSE 2022 (co-located with ICSE'22).

Mar 2, 2022. | By: Mohammed Latif Siddiq

Our paper, “BERT-Based GitHub Issue Report Classification”, got accepted for The 1st Intl. Workshop on Natural Language-based Software Engineering (NLBSE’22) co-located with ICSE 2022 in the tool competition. we describe a BERT-based classification technique to automatically label issues as questions, bugs, or enhancements. We evaluate our approach using a dataset containing over 800,000 labeled issues from real open source projects available on GitHub. Our approach classified reported issues with an average F1-score of 0.8571. Our technique outperforms a previous machine learning technique based on FastText.

Related Links

BibTeX

@inproceedings{siddiq2022bert,
  author = {M. Siddiq and J. C. S. Santos},
  booktitle = {2022 IEEE/ACM 1st International Workshop on Natural Language-Based Software Engineering (NLBSE)},
  title = {{BERT}-Based GitHub Issue Report Classification},
  year = {2022},
  volume = {1},
  issn = {978-1-4503-9343-0},
  pages = {33-36},
  keywords = {software maintenance;conferences;computer bugs;machine learning;natural language processing;labeling;task analysis},
  doi = {10.1145/3528588.3528660},
  url = {https://doi.ieeecomputersociety.org/},
  publisher = {IEEE Computer Society},
  address = {Los Alamitos, CA, USA},
  month = {may}
}

About

Security and Software Engineering Lab at University of Notre Dame, Notre Dame, IN USA 46556

twitter github

Where We Are

University of Notre Dame
College of Engineering
382 Fitzpatrick Hall
Notre Dame, IN 46556