Loading…

Improving Bug Severity Prediction with Domain-Specific Representation Learning

Automating the process of bug severity assignment can accelerate bug triagers' efficiency in the life-cycle of software maintenance, improving the quality of software products. The mainstream approaches for bug severity prediction mainly use different neural networks due to their automated lear...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2023-01, Vol.11, p.1-1
Main Authors: Wei, Ye, Zhang, Chunfu, Ren, Teng
Format: Article
Language:English
Subjects:
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c409t-855a79594a74f6d65a540cd8d7a2ae270e6c3a4b5bb673ad833c3565c12c8db23
cites cdi_FETCH-LOGICAL-c409t-855a79594a74f6d65a540cd8d7a2ae270e6c3a4b5bb673ad833c3565c12c8db23
container_end_page 1
container_issue
container_start_page 1
container_title IEEE access
container_volume 11
creator Wei, Ye
Zhang, Chunfu
Ren, Teng
description Automating the process of bug severity assignment can accelerate bug triagers' efficiency in the life-cycle of software maintenance, improving the quality of software products. The mainstream approaches for bug severity prediction mainly use different neural networks due to their automated learning ability. However, there are two problems that make existing approaches fail to predict severities for some bugs: 1) they cannot learn the internal knowledge of bug reports; 2) supervised training is difficult to understand the global context of bug reports. To resolve these two problems, in this paper, we propose a bug severity prediction approach, namely KICL, which combines pre-trained language models and domain-specific pre-training strategies, i.e., Knowledge-Intensified pre-training and contrastive learning pre-training. Specifically, Knowledge-Intensified allows KICL to learn project-specific bug report tokens, deeply understanding internal knowledge of bug reports. As for contrastive learning, it allows KICL to perform sequence-level learning, understanding bug reports from the perspective of the global context. When finishing pre-training, we can fine-tune pre-trained KICL for bug severity prediction. To evaluate the effectiveness of KICL, we choose six baseline approaches and compare their performance on a public dataset. The experimental results show that KICL outperforms all baseline approaches by up to 30.68% in terms of weighted average F1-score, achieving new results for bug severity prediction.
doi_str_mv 10.1109/ACCESS.2023.3279205
format article
fullrecord <record><control><sourceid>proquest_doaj_</sourceid><recordid>TN_cdi_doaj_primary_oai_doaj_org_article_4d42a582df7641cd9918fd9bf55bbfb5</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10131903</ieee_id><doaj_id>oai_doaj_org_article_4d42a582df7641cd9918fd9bf55bbfb5</doaj_id><sourcerecordid>2830415492</sourcerecordid><originalsourceid>FETCH-LOGICAL-c409t-855a79594a74f6d65a540cd8d7a2ae270e6c3a4b5bb673ad833c3565c12c8db23</originalsourceid><addsrcrecordid>eNpNkU1PwzAMhiMEEtPYL4BDJc4d-Wyb4xhfkyZAFM5Rmrgj09aUtBvav6dbJzRfbFl-H1t-EbomeEwIlneT6fQxz8cUUzZmNJUUizM0oCSRMRMsOT-pL9GoaZa4i6xriXSAXmfrOvitqxbR_WYR5bCF4Npd9B7AOtM6X0W_rv2OHvxauyrOazCudCb6gDpAA1WrDzNz0KHqIFfootSrBkbHPERfT4-f05d4_vY8m07mseFYtnEmhE6lkFynvExsIrTg2NjMpppqoCmGxDDNC1EUScq0zRgzTCTCEGoyW1A2RLOea71eqjq4tQ475bVTh4YPC6VD68wKFLecapFRW6YJJ8ZKSbLSyqIUHb0sRMe67VndI3420LRq6Teh6s5XNGOYE8HlfiPrp0zwTROg_N9KsNr7oHof1N4HdfShU930KgcAJwrCiMSM_QFlHIQV</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2830415492</pqid></control><display><type>article</type><title>Improving Bug Severity Prediction with Domain-Specific Representation Learning</title><source>IEEE Open Access Journals</source><creator>Wei, Ye ; Zhang, Chunfu ; Ren, Teng</creator><creatorcontrib>Wei, Ye ; Zhang, Chunfu ; Ren, Teng</creatorcontrib><description>Automating the process of bug severity assignment can accelerate bug triagers' efficiency in the life-cycle of software maintenance, improving the quality of software products. The mainstream approaches for bug severity prediction mainly use different neural networks due to their automated learning ability. However, there are two problems that make existing approaches fail to predict severities for some bugs: 1) they cannot learn the internal knowledge of bug reports; 2) supervised training is difficult to understand the global context of bug reports. To resolve these two problems, in this paper, we propose a bug severity prediction approach, namely KICL, which combines pre-trained language models and domain-specific pre-training strategies, i.e., Knowledge-Intensified pre-training and contrastive learning pre-training. Specifically, Knowledge-Intensified allows KICL to learn project-specific bug report tokens, deeply understanding internal knowledge of bug reports. As for contrastive learning, it allows KICL to perform sequence-level learning, understanding bug reports from the perspective of the global context. When finishing pre-training, we can fine-tune pre-trained KICL for bug severity prediction. To evaluate the effectiveness of KICL, we choose six baseline approaches and compare their performance on a public dataset. The experimental results show that KICL outperforms all baseline approaches by up to 30.68% in terms of weighted average F1-score, achieving new results for bug severity prediction.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2023.3279205</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Automation ; Bug severity prediction ; Computer bugs ; Context ; Debugging ; domain-specific pre-training ; Learning ; Neural networks ; pre-trained language model ; Predictive models ; Representation learning ; Semantics ; Software ; Software maintenance ; Task analysis ; Training ; Transformers</subject><ispartof>IEEE access, 2023-01, Vol.11, p.1-1</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2023</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c409t-855a79594a74f6d65a540cd8d7a2ae270e6c3a4b5bb673ad833c3565c12c8db23</citedby><cites>FETCH-LOGICAL-c409t-855a79594a74f6d65a540cd8d7a2ae270e6c3a4b5bb673ad833c3565c12c8db23</cites><orcidid>0009-0001-7090-414X ; 0009-0006-0568-9128</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10131903$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,27633,27924,27925,54933</link.rule.ids></links><search><creatorcontrib>Wei, Ye</creatorcontrib><creatorcontrib>Zhang, Chunfu</creatorcontrib><creatorcontrib>Ren, Teng</creatorcontrib><title>Improving Bug Severity Prediction with Domain-Specific Representation Learning</title><title>IEEE access</title><addtitle>Access</addtitle><description>Automating the process of bug severity assignment can accelerate bug triagers' efficiency in the life-cycle of software maintenance, improving the quality of software products. The mainstream approaches for bug severity prediction mainly use different neural networks due to their automated learning ability. However, there are two problems that make existing approaches fail to predict severities for some bugs: 1) they cannot learn the internal knowledge of bug reports; 2) supervised training is difficult to understand the global context of bug reports. To resolve these two problems, in this paper, we propose a bug severity prediction approach, namely KICL, which combines pre-trained language models and domain-specific pre-training strategies, i.e., Knowledge-Intensified pre-training and contrastive learning pre-training. Specifically, Knowledge-Intensified allows KICL to learn project-specific bug report tokens, deeply understanding internal knowledge of bug reports. As for contrastive learning, it allows KICL to perform sequence-level learning, understanding bug reports from the perspective of the global context. When finishing pre-training, we can fine-tune pre-trained KICL for bug severity prediction. To evaluate the effectiveness of KICL, we choose six baseline approaches and compare their performance on a public dataset. The experimental results show that KICL outperforms all baseline approaches by up to 30.68% in terms of weighted average F1-score, achieving new results for bug severity prediction.</description><subject>Automation</subject><subject>Bug severity prediction</subject><subject>Computer bugs</subject><subject>Context</subject><subject>Debugging</subject><subject>domain-specific pre-training</subject><subject>Learning</subject><subject>Neural networks</subject><subject>pre-trained language model</subject><subject>Predictive models</subject><subject>Representation learning</subject><subject>Semantics</subject><subject>Software</subject><subject>Software maintenance</subject><subject>Task analysis</subject><subject>Training</subject><subject>Transformers</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>DOA</sourceid><recordid>eNpNkU1PwzAMhiMEEtPYL4BDJc4d-Wyb4xhfkyZAFM5Rmrgj09aUtBvav6dbJzRfbFl-H1t-EbomeEwIlneT6fQxz8cUUzZmNJUUizM0oCSRMRMsOT-pL9GoaZa4i6xriXSAXmfrOvitqxbR_WYR5bCF4Npd9B7AOtM6X0W_rv2OHvxauyrOazCudCb6gDpAA1WrDzNz0KHqIFfootSrBkbHPERfT4-f05d4_vY8m07mseFYtnEmhE6lkFynvExsIrTg2NjMpppqoCmGxDDNC1EUScq0zRgzTCTCEGoyW1A2RLOea71eqjq4tQ475bVTh4YPC6VD68wKFLecapFRW6YJJ8ZKSbLSyqIUHb0sRMe67VndI3420LRq6Teh6s5XNGOYE8HlfiPrp0zwTROg_N9KsNr7oHof1N4HdfShU930KgcAJwrCiMSM_QFlHIQV</recordid><startdate>20230101</startdate><enddate>20230101</enddate><creator>Wei, Ye</creator><creator>Zhang, Chunfu</creator><creator>Ren, Teng</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7SR</scope><scope>8BQ</scope><scope>8FD</scope><scope>JG9</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>DOA</scope><orcidid>https://orcid.org/0009-0001-7090-414X</orcidid><orcidid>https://orcid.org/0009-0006-0568-9128</orcidid></search><sort><creationdate>20230101</creationdate><title>Improving Bug Severity Prediction with Domain-Specific Representation Learning</title><author>Wei, Ye ; Zhang, Chunfu ; Ren, Teng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c409t-855a79594a74f6d65a540cd8d7a2ae270e6c3a4b5bb673ad833c3565c12c8db23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Automation</topic><topic>Bug severity prediction</topic><topic>Computer bugs</topic><topic>Context</topic><topic>Debugging</topic><topic>domain-specific pre-training</topic><topic>Learning</topic><topic>Neural networks</topic><topic>pre-trained language model</topic><topic>Predictive models</topic><topic>Representation learning</topic><topic>Semantics</topic><topic>Software</topic><topic>Software maintenance</topic><topic>Task analysis</topic><topic>Training</topic><topic>Transformers</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Wei, Ye</creatorcontrib><creatorcontrib>Zhang, Chunfu</creatorcontrib><creatorcontrib>Ren, Teng</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005–Present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Xplore</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Engineered Materials Abstracts</collection><collection>METADEX</collection><collection>Technology Research Database</collection><collection>Materials Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts – Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wei, Ye</au><au>Zhang, Chunfu</au><au>Ren, Teng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Improving Bug Severity Prediction with Domain-Specific Representation Learning</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2023-01-01</date><risdate>2023</risdate><volume>11</volume><spage>1</spage><epage>1</epage><pages>1-1</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Automating the process of bug severity assignment can accelerate bug triagers' efficiency in the life-cycle of software maintenance, improving the quality of software products. The mainstream approaches for bug severity prediction mainly use different neural networks due to their automated learning ability. However, there are two problems that make existing approaches fail to predict severities for some bugs: 1) they cannot learn the internal knowledge of bug reports; 2) supervised training is difficult to understand the global context of bug reports. To resolve these two problems, in this paper, we propose a bug severity prediction approach, namely KICL, which combines pre-trained language models and domain-specific pre-training strategies, i.e., Knowledge-Intensified pre-training and contrastive learning pre-training. Specifically, Knowledge-Intensified allows KICL to learn project-specific bug report tokens, deeply understanding internal knowledge of bug reports. As for contrastive learning, it allows KICL to perform sequence-level learning, understanding bug reports from the perspective of the global context. When finishing pre-training, we can fine-tune pre-trained KICL for bug severity prediction. To evaluate the effectiveness of KICL, we choose six baseline approaches and compare their performance on a public dataset. The experimental results show that KICL outperforms all baseline approaches by up to 30.68% in terms of weighted average F1-score, achieving new results for bug severity prediction.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2023.3279205</doi><tpages>1</tpages><orcidid>https://orcid.org/0009-0001-7090-414X</orcidid><orcidid>https://orcid.org/0009-0006-0568-9128</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 2169-3536
ispartof IEEE access, 2023-01, Vol.11, p.1-1
issn 2169-3536
2169-3536
language eng
recordid cdi_doaj_primary_oai_doaj_org_article_4d42a582df7641cd9918fd9bf55bbfb5
source IEEE Open Access Journals
subjects Automation
Bug severity prediction
Computer bugs
Context
Debugging
domain-specific pre-training
Learning
Neural networks
pre-trained language model
Predictive models
Representation learning
Semantics
Software
Software maintenance
Task analysis
Training
Transformers
title Improving Bug Severity Prediction with Domain-Specific Representation Learning
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T12%3A02%3A11IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_doaj_&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Improving%20Bug%20Severity%20Prediction%20with%20Domain-Specific%20Representation%20Learning&rft.jtitle=IEEE%20access&rft.au=Wei,%20Ye&rft.date=2023-01-01&rft.volume=11&rft.spage=1&rft.epage=1&rft.pages=1-1&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2023.3279205&rft_dat=%3Cproquest_doaj_%3E2830415492%3C/proquest_doaj_%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c409t-855a79594a74f6d65a540cd8d7a2ae270e6c3a4b5bb673ad833c3565c12c8db23%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2830415492&rft_id=info:pmid/&rft_ieee_id=10131903&rfr_iscdi=true