Loading…
Applying Convolutional Neural Networks With Different Word Representation Techniques to Recommend Bug Fixers
Bug triage processes are intended to assign bug reports to appropriate developers effectively, but they typically become bottlenecks in the development process-especially for large-scale software projects. Recently, several machine learning approaches, including deep learning-based approaches, have...
Saved in:
Published in: | IEEE access 2020, Vol.8, p.213729-213747 |
---|---|
Main Authors: | , , , , |
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-c408t-3e61487cd5683106655ef0b9fd77d1d0eff04d59935e04702c15d53b7d3a68c13 |
---|---|
cites | cdi_FETCH-LOGICAL-c408t-3e61487cd5683106655ef0b9fd77d1d0eff04d59935e04702c15d53b7d3a68c13 |
container_end_page | 213747 |
container_issue | |
container_start_page | 213729 |
container_title | IEEE access |
container_volume | 8 |
creator | Zaidi, Syed Farhan Alam Awan, Faraz Malik Lee, Minsoo Woo, Honguk Lee, Chan-Gun |
description | Bug triage processes are intended to assign bug reports to appropriate developers effectively, but they typically become bottlenecks in the development process-especially for large-scale software projects. Recently, several machine learning approaches, including deep learning-based approaches, have been proposed to recommend an appropriate developer automatically by learning past assignment patterns. In this paper, we propose a deep learning-based bug triage technique using a convolutional neural network (CNN) with three different word representation techniques: Word to Vector (Word2Vec), Global Vector (GloVe), and Embeddings from Language Models (ELMo). Experiments were performed on datasets from well-known large-scale open-source projects, such as Eclipse and Mozilla, and top-k accuracy was measured as an evaluation metric. The experimental results suggest that the ELMo-based CNN approach performs best for the bug triage problem. GloVe-based CNN slightly outperforms Word2Vec-based CNN in many cases. Word2Vec-based CNN outperforms GloVe-based CNN when the number of samples per class in the dataset is high enough. |
doi_str_mv | 10.1109/ACCESS.2020.3040065 |
format | article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1109_ACCESS_2020_3040065</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9268164</ieee_id><doaj_id>oai_doaj_org_article_cff2af7a93f741eebab14664b1320465</doaj_id><sourcerecordid>2468760554</sourcerecordid><originalsourceid>FETCH-LOGICAL-c408t-3e61487cd5683106655ef0b9fd77d1d0eff04d59935e04702c15d53b7d3a68c13</originalsourceid><addsrcrecordid>eNpNkU1P3DAQhqOqSEWUX8DFUs-7HccfSY7bFAoSaiWg4mg59njxNhundlLg3-MlCNWX8Xy8r-V5iuKMwppSaL5u2vb89nZdQglrBhxAig_FcUlls2KCyY__3T8VpyntIJ86l0R1XPSbceyf_bAlbRj-hX6efBh0T37iHF_D9Bjin0Tu_fRAvnvnMOIwkfsQLbnBMWLKqT6IyB2ah8H_nTGRKeSmCfs9DpZ8m7fkwj9hTJ-LI6f7hKdv8aT4fXF-116urn_9uGo31yvDoZ5WDCXldWWskDWjIKUQ6KBrnK0qSy2gc8CtaBomEHgFpaHCCtZVlmlZG8pOiqvF1wa9U2P0ex2fVdBevRZC3CodJ296VMa5UrtKN8xVnCJ2uqNcSt5RVgKXInt9WbzGGA5_m9QuzDGvKKmSy7qSIATPU2yZMjGkFNG9v0pBHSiphZI6UFJvlLLqbFF5RHxXNKXMdDh7AWg2jmA</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2468760554</pqid></control><display><type>article</type><title>Applying Convolutional Neural Networks With Different Word Representation Techniques to Recommend Bug Fixers</title><source>IEEE Open Access Journals</source><creator>Zaidi, Syed Farhan Alam ; Awan, Faraz Malik ; Lee, Minsoo ; Woo, Honguk ; Lee, Chan-Gun</creator><creatorcontrib>Zaidi, Syed Farhan Alam ; Awan, Faraz Malik ; Lee, Minsoo ; Woo, Honguk ; Lee, Chan-Gun</creatorcontrib><description>Bug triage processes are intended to assign bug reports to appropriate developers effectively, but they typically become bottlenecks in the development process-especially for large-scale software projects. Recently, several machine learning approaches, including deep learning-based approaches, have been proposed to recommend an appropriate developer automatically by learning past assignment patterns. In this paper, we propose a deep learning-based bug triage technique using a convolutional neural network (CNN) with three different word representation techniques: Word to Vector (Word2Vec), Global Vector (GloVe), and Embeddings from Language Models (ELMo). Experiments were performed on datasets from well-known large-scale open-source projects, such as Eclipse and Mozilla, and top-k accuracy was measured as an evaluation metric. The experimental results suggest that the ELMo-based CNN approach performs best for the bug triage problem. GloVe-based CNN slightly outperforms Word2Vec-based CNN in many cases. Word2Vec-based CNN outperforms GloVe-based CNN when the number of samples per class in the dataset is high enough.</description><identifier>ISSN: 2169-3536</identifier><identifier>EISSN: 2169-3536</identifier><identifier>DOI: 10.1109/ACCESS.2020.3040065</identifier><identifier>CODEN: IAECCG</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Artificial neural networks ; bug fixing ; bug report ; Bug triage ; CNN ; Computer bugs ; Datasets ; Deep learning ; ELMo ; Feature extraction ; GloVe ; Machine learning ; Neural networks ; Open source software ; recommending bug fixer ; Recurrent neural networks ; Representations ; Source code ; Support vector machines ; Task analysis ; word embedding ; word representation ; Word2Vec ; Words (language)</subject><ispartof>IEEE access, 2020, Vol.8, p.213729-213747</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2020</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c408t-3e61487cd5683106655ef0b9fd77d1d0eff04d59935e04702c15d53b7d3a68c13</citedby><cites>FETCH-LOGICAL-c408t-3e61487cd5683106655ef0b9fd77d1d0eff04d59935e04702c15d53b7d3a68c13</cites><orcidid>0000-0003-2257-290X ; 0000-0001-9674-0625 ; 0000-0001-9734-4456 ; 0000-0001-6948-3440</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9268164$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,4024,27633,27923,27924,27925,54933</link.rule.ids></links><search><creatorcontrib>Zaidi, Syed Farhan Alam</creatorcontrib><creatorcontrib>Awan, Faraz Malik</creatorcontrib><creatorcontrib>Lee, Minsoo</creatorcontrib><creatorcontrib>Woo, Honguk</creatorcontrib><creatorcontrib>Lee, Chan-Gun</creatorcontrib><title>Applying Convolutional Neural Networks With Different Word Representation Techniques to Recommend Bug Fixers</title><title>IEEE access</title><addtitle>Access</addtitle><description>Bug triage processes are intended to assign bug reports to appropriate developers effectively, but they typically become bottlenecks in the development process-especially for large-scale software projects. Recently, several machine learning approaches, including deep learning-based approaches, have been proposed to recommend an appropriate developer automatically by learning past assignment patterns. In this paper, we propose a deep learning-based bug triage technique using a convolutional neural network (CNN) with three different word representation techniques: Word to Vector (Word2Vec), Global Vector (GloVe), and Embeddings from Language Models (ELMo). Experiments were performed on datasets from well-known large-scale open-source projects, such as Eclipse and Mozilla, and top-k accuracy was measured as an evaluation metric. The experimental results suggest that the ELMo-based CNN approach performs best for the bug triage problem. GloVe-based CNN slightly outperforms Word2Vec-based CNN in many cases. Word2Vec-based CNN outperforms GloVe-based CNN when the number of samples per class in the dataset is high enough.</description><subject>Artificial neural networks</subject><subject>bug fixing</subject><subject>bug report</subject><subject>Bug triage</subject><subject>CNN</subject><subject>Computer bugs</subject><subject>Datasets</subject><subject>Deep learning</subject><subject>ELMo</subject><subject>Feature extraction</subject><subject>GloVe</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Open source software</subject><subject>recommending bug fixer</subject><subject>Recurrent neural networks</subject><subject>Representations</subject><subject>Source code</subject><subject>Support vector machines</subject><subject>Task analysis</subject><subject>word embedding</subject><subject>word representation</subject><subject>Word2Vec</subject><subject>Words (language)</subject><issn>2169-3536</issn><issn>2169-3536</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2020</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>DOA</sourceid><recordid>eNpNkU1P3DAQhqOqSEWUX8DFUs-7HccfSY7bFAoSaiWg4mg59njxNhundlLg3-MlCNWX8Xy8r-V5iuKMwppSaL5u2vb89nZdQglrBhxAig_FcUlls2KCyY__3T8VpyntIJ86l0R1XPSbceyf_bAlbRj-hX6efBh0T37iHF_D9Bjin0Tu_fRAvnvnMOIwkfsQLbnBMWLKqT6IyB2ah8H_nTGRKeSmCfs9DpZ8m7fkwj9hTJ-LI6f7hKdv8aT4fXF-116urn_9uGo31yvDoZ5WDCXldWWskDWjIKUQ6KBrnK0qSy2gc8CtaBomEHgFpaHCCtZVlmlZG8pOiqvF1wa9U2P0ex2fVdBevRZC3CodJ296VMa5UrtKN8xVnCJ2uqNcSt5RVgKXInt9WbzGGA5_m9QuzDGvKKmSy7qSIATPU2yZMjGkFNG9v0pBHSiphZI6UFJvlLLqbFF5RHxXNKXMdDh7AWg2jmA</recordid><startdate>2020</startdate><enddate>2020</enddate><creator>Zaidi, Syed Farhan Alam</creator><creator>Awan, Faraz Malik</creator><creator>Lee, Minsoo</creator><creator>Woo, Honguk</creator><creator>Lee, Chan-Gun</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/0000-0003-2257-290X</orcidid><orcidid>https://orcid.org/0000-0001-9674-0625</orcidid><orcidid>https://orcid.org/0000-0001-9734-4456</orcidid><orcidid>https://orcid.org/0000-0001-6948-3440</orcidid></search><sort><creationdate>2020</creationdate><title>Applying Convolutional Neural Networks With Different Word Representation Techniques to Recommend Bug Fixers</title><author>Zaidi, Syed Farhan Alam ; Awan, Faraz Malik ; Lee, Minsoo ; Woo, Honguk ; Lee, Chan-Gun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c408t-3e61487cd5683106655ef0b9fd77d1d0eff04d59935e04702c15d53b7d3a68c13</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2020</creationdate><topic>Artificial neural networks</topic><topic>bug fixing</topic><topic>bug report</topic><topic>Bug triage</topic><topic>CNN</topic><topic>Computer bugs</topic><topic>Datasets</topic><topic>Deep learning</topic><topic>ELMo</topic><topic>Feature extraction</topic><topic>GloVe</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Open source software</topic><topic>recommending bug fixer</topic><topic>Recurrent neural networks</topic><topic>Representations</topic><topic>Source code</topic><topic>Support vector machines</topic><topic>Task analysis</topic><topic>word embedding</topic><topic>word representation</topic><topic>Word2Vec</topic><topic>Words (language)</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zaidi, Syed Farhan Alam</creatorcontrib><creatorcontrib>Awan, Faraz Malik</creatorcontrib><creatorcontrib>Lee, Minsoo</creatorcontrib><creatorcontrib>Woo, Honguk</creatorcontrib><creatorcontrib>Lee, Chan-Gun</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 Electronic Library Online</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & 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>Directory of Open Access Journals</collection><jtitle>IEEE access</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zaidi, Syed Farhan Alam</au><au>Awan, Faraz Malik</au><au>Lee, Minsoo</au><au>Woo, Honguk</au><au>Lee, Chan-Gun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Applying Convolutional Neural Networks With Different Word Representation Techniques to Recommend Bug Fixers</atitle><jtitle>IEEE access</jtitle><stitle>Access</stitle><date>2020</date><risdate>2020</risdate><volume>8</volume><spage>213729</spage><epage>213747</epage><pages>213729-213747</pages><issn>2169-3536</issn><eissn>2169-3536</eissn><coden>IAECCG</coden><abstract>Bug triage processes are intended to assign bug reports to appropriate developers effectively, but they typically become bottlenecks in the development process-especially for large-scale software projects. Recently, several machine learning approaches, including deep learning-based approaches, have been proposed to recommend an appropriate developer automatically by learning past assignment patterns. In this paper, we propose a deep learning-based bug triage technique using a convolutional neural network (CNN) with three different word representation techniques: Word to Vector (Word2Vec), Global Vector (GloVe), and Embeddings from Language Models (ELMo). Experiments were performed on datasets from well-known large-scale open-source projects, such as Eclipse and Mozilla, and top-k accuracy was measured as an evaluation metric. The experimental results suggest that the ELMo-based CNN approach performs best for the bug triage problem. GloVe-based CNN slightly outperforms Word2Vec-based CNN in many cases. Word2Vec-based CNN outperforms GloVe-based CNN when the number of samples per class in the dataset is high enough.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/ACCESS.2020.3040065</doi><tpages>19</tpages><orcidid>https://orcid.org/0000-0003-2257-290X</orcidid><orcidid>https://orcid.org/0000-0001-9674-0625</orcidid><orcidid>https://orcid.org/0000-0001-9734-4456</orcidid><orcidid>https://orcid.org/0000-0001-6948-3440</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2169-3536 |
ispartof | IEEE access, 2020, Vol.8, p.213729-213747 |
issn | 2169-3536 2169-3536 |
language | eng |
recordid | cdi_crossref_primary_10_1109_ACCESS_2020_3040065 |
source | IEEE Open Access Journals |
subjects | Artificial neural networks bug fixing bug report Bug triage CNN Computer bugs Datasets Deep learning ELMo Feature extraction GloVe Machine learning Neural networks Open source software recommending bug fixer Recurrent neural networks Representations Source code Support vector machines Task analysis word embedding word representation Word2Vec Words (language) |
title | Applying Convolutional Neural Networks With Different Word Representation Techniques to Recommend Bug Fixers |
url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-23T04%3A27%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Applying%20Convolutional%20Neural%20Networks%20With%20Different%20Word%20Representation%20Techniques%20to%20Recommend%20Bug%20Fixers&rft.jtitle=IEEE%20access&rft.au=Zaidi,%20Syed%20Farhan%20Alam&rft.date=2020&rft.volume=8&rft.spage=213729&rft.epage=213747&rft.pages=213729-213747&rft.issn=2169-3536&rft.eissn=2169-3536&rft.coden=IAECCG&rft_id=info:doi/10.1109/ACCESS.2020.3040065&rft_dat=%3Cproquest_cross%3E2468760554%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c408t-3e61487cd5683106655ef0b9fd77d1d0eff04d59935e04702c15d53b7d3a68c13%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2468760554&rft_id=info:pmid/&rft_ieee_id=9268164&rfr_iscdi=true |