A Comparative Study of Contemporary Learning Paradigms in Bug Report Priority Detection

<p dir="ltr">The increasing complexity of software development demands efficient automated bug report priority classification, and recent advancements in deep learning hold promise. This paper presents a comparative study of contemporary learning paradigms, including BERT, vector dat...

Full description

Saved in:
Bibliographic Details
Main Author: Eyüp Halit Yilmaz (21400700) (author)
Other Authors: İsmail Hakki Toroslu (21400703) (author), Ömer Köksal (21400706) (author)
Published: 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513543591690240
author Eyüp Halit Yilmaz (21400700)
author2 İsmail Hakki Toroslu (21400703)
Ömer Köksal (21400706)
author2_role author
author
author_facet Eyüp Halit Yilmaz (21400700)
İsmail Hakki Toroslu (21400703)
Ömer Köksal (21400706)
author_role author
dc.creator.none.fl_str_mv Eyüp Halit Yilmaz (21400700)
İsmail Hakki Toroslu (21400703)
Ömer Köksal (21400706)
dc.date.none.fl_str_mv 2024-08-28T06:00:00Z
dc.identifier.none.fl_str_mv 10.1109/ACCESS.2024.3451125
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_Comparative_Study_of_Contemporary_Learning_Paradigms_in_Bug_Report_Priority_Detection/29605112
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Applied computing
Artificial intelligence
Data management and data science
Machine learning
Software engineering
Bug triaging
Contrastive learning
Machine learning
Natural language processing
Software bug report classification
Software engineering
dc.title.none.fl_str_mv A Comparative Study of Contemporary Learning Paradigms in Bug Report Priority Detection
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">The increasing complexity of software development demands efficient automated bug report priority classification, and recent advancements in deep learning hold promise. This paper presents a comparative study of contemporary learning paradigms, including BERT, vector databases, large language models (LLMs), and a simple novel learning paradigm, contrastive learning for BERT. Utilizing datasets from bug reports, movie reviews, and app reviews, we evaluate and compare the performance of each approach. We find that transformer encoder-only models outperform in classification tasks measured by the precision, recall, and F1 score transformer decoder-only models despite an order of magnitude gap between the number of parameters. The novel use of contrastive learning for BERT demonstrates promising results in capturing subtle nuances in text data. This work highlights the potential of advanced NLP techniques for automated bug report priority classification and underscores the importance of considering multiple factors when developing models for this task. The paper’s main contributions are a comprehensive evaluation of various learning paradigms, such as vector databases and LLMs, an introduction of contrastive learning for BERT, an exploration of applicability to other text classification tasks, and a contrastive learning procedure that exploits ordinal information between classes.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" rel="noreferrer noopener" target="_blank">https://creativecommons.org/licenses/by/4.0/</a>  <br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2024.3451125" target="_blank">https://dx.doi.org/10.1109/access.2024.3451125</a></p>
eu_rights_str_mv openAccess
id Manara2_554d68e988cea3758224f90bc5c42688
identifier_str_mv 10.1109/ACCESS.2024.3451125
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/29605112
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A Comparative Study of Contemporary Learning Paradigms in Bug Report Priority DetectionEyüp Halit Yilmaz (21400700)İsmail Hakki Toroslu (21400703)Ömer Köksal (21400706)Information and computing sciencesApplied computingArtificial intelligenceData management and data scienceMachine learningSoftware engineeringBug triagingContrastive learningMachine learningNatural language processingSoftware bug report classificationSoftware engineering<p dir="ltr">The increasing complexity of software development demands efficient automated bug report priority classification, and recent advancements in deep learning hold promise. This paper presents a comparative study of contemporary learning paradigms, including BERT, vector databases, large language models (LLMs), and a simple novel learning paradigm, contrastive learning for BERT. Utilizing datasets from bug reports, movie reviews, and app reviews, we evaluate and compare the performance of each approach. We find that transformer encoder-only models outperform in classification tasks measured by the precision, recall, and F1 score transformer decoder-only models despite an order of magnitude gap between the number of parameters. The novel use of contrastive learning for BERT demonstrates promising results in capturing subtle nuances in text data. This work highlights the potential of advanced NLP techniques for automated bug report priority classification and underscores the importance of considering multiple factors when developing models for this task. The paper’s main contributions are a comprehensive evaluation of various learning paradigms, such as vector databases and LLMs, an introduction of contrastive learning for BERT, an exploration of applicability to other text classification tasks, and a contrastive learning procedure that exploits ordinal information between classes.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" rel="noreferrer noopener" target="_blank">https://creativecommons.org/licenses/by/4.0/</a>  <br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2024.3451125" target="_blank">https://dx.doi.org/10.1109/access.2024.3451125</a></p>2024-08-28T06:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/ACCESS.2024.3451125https://figshare.com/articles/journal_contribution/A_Comparative_Study_of_Contemporary_Learning_Paradigms_in_Bug_Report_Priority_Detection/29605112CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/296051122024-08-28T06:00:00Z
spellingShingle A Comparative Study of Contemporary Learning Paradigms in Bug Report Priority Detection
Eyüp Halit Yilmaz (21400700)
Information and computing sciences
Applied computing
Artificial intelligence
Data management and data science
Machine learning
Software engineering
Bug triaging
Contrastive learning
Machine learning
Natural language processing
Software bug report classification
Software engineering
status_str publishedVersion
title A Comparative Study of Contemporary Learning Paradigms in Bug Report Priority Detection
title_full A Comparative Study of Contemporary Learning Paradigms in Bug Report Priority Detection
title_fullStr A Comparative Study of Contemporary Learning Paradigms in Bug Report Priority Detection
title_full_unstemmed A Comparative Study of Contemporary Learning Paradigms in Bug Report Priority Detection
title_short A Comparative Study of Contemporary Learning Paradigms in Bug Report Priority Detection
title_sort A Comparative Study of Contemporary Learning Paradigms in Bug Report Priority Detection
topic Information and computing sciences
Applied computing
Artificial intelligence
Data management and data science
Machine learning
Software engineering
Bug triaging
Contrastive learning
Machine learning
Natural language processing
Software bug report classification
Software engineering