{"id":"https://openalex.org/W2735731932","doi":"https://doi.org/10.1109/ijcnn.2017.7965999","title":"Classifying commit messages: A case study in resampling techniques","display_name":"Classifying commit messages: A case study in resampling techniques","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2735731932","doi":"https://doi.org/10.1109/ijcnn.2017.7965999","mag":"2735731932"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2017.7965999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047329370","display_name":"SeyedHamid Shekarforoush","orcid":null},"institutions":[{"id":"https://openalex.org/I157417397","display_name":"Bowling Green State University","ror":"https://ror.org/00ay7va13","country_code":"US","type":"education","lineage":["https://openalex.org/I157417397"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"SeyedHamid Shekarforoush","raw_affiliation_strings":["Bowling Green State University, Bowling Green, OH, USA"],"affiliations":[{"raw_affiliation_string":"Bowling Green State University, Bowling Green, OH, USA","institution_ids":["https://openalex.org/I157417397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075565472","display_name":"Robert Green","orcid":"https://orcid.org/0000-0002-3792-2725"},"institutions":[{"id":"https://openalex.org/I157417397","display_name":"Bowling Green State University","ror":"https://ror.org/00ay7va13","country_code":"US","type":"education","lineage":["https://openalex.org/I157417397"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Green","raw_affiliation_strings":["Bowling Green State University, Bowling Green, OH, USA"],"affiliations":[{"raw_affiliation_string":"Bowling Green State University, Bowling Green, OH, USA","institution_ids":["https://openalex.org/I157417397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057293289","display_name":"Robert Dyer","orcid":"https://orcid.org/0000-0001-9571-5567"},"institutions":[{"id":"https://openalex.org/I157417397","display_name":"Bowling Green State University","ror":"https://ror.org/00ay7va13","country_code":"US","type":"education","lineage":["https://openalex.org/I157417397"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Dyer","raw_affiliation_strings":["Bowling Green State University, Bowling Green, OH, USA"],"affiliations":[{"raw_affiliation_string":"Bowling Green State University, Bowling Green, OH, USA","institution_ids":["https://openalex.org/I157417397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047329370"],"corresponding_institution_ids":["https://openalex.org/I157417397"],"apc_list":null,"apc_paid":null,"fwci":0.9751,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.81852248,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1273","last_page":"1280"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/commit","display_name":"Commit","score":0.9419242143630981},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.8737127780914307},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8081178069114685},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6615841388702393},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.6215287446975708},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5736093521118164},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5603233575820923},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5555263757705688},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5401910543441772},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5340403914451599},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.48341691493988037},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41462036967277527},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11760792136192322},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07824403047561646}],"concepts":[{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.9419242143630981},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.8737127780914307},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8081178069114685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6615841388702393},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.6215287446975708},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5736093521118164},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5603233575820923},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5555263757705688},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5401910543441772},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5340403914451599},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.48341691493988037},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41462036967277527},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11760792136192322},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07824403047561646},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2017.7965999","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2017.7965999","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W85350352","https://openalex.org/W961659484","https://openalex.org/W1550206324","https://openalex.org/W1576442155","https://openalex.org/W1591261915","https://openalex.org/W1964357740","https://openalex.org/W1993220166","https://openalex.org/W1994410331","https://openalex.org/W2022477494","https://openalex.org/W2095148636","https://openalex.org/W2101234009","https://openalex.org/W2104167780","https://openalex.org/W2104933073","https://openalex.org/W2107432340","https://openalex.org/W2107686700","https://openalex.org/W2118585731","https://openalex.org/W2132791018","https://openalex.org/W2137029138","https://openalex.org/W2138550913","https://openalex.org/W2148143831","https://openalex.org/W2168508521","https://openalex.org/W2330820318","https://openalex.org/W2548610994","https://openalex.org/W2911964244","https://openalex.org/W2979832949","https://openalex.org/W3155649056","https://openalex.org/W4235456164","https://openalex.org/W4293713156","https://openalex.org/W6603460400","https://openalex.org/W6632865047","https://openalex.org/W6634357899","https://openalex.org/W6635474240","https://openalex.org/W6675354045","https://openalex.org/W6675634716","https://openalex.org/W6677656871","https://openalex.org/W6682141768"],"related_works":["https://openalex.org/W4367365664","https://openalex.org/W4293227618","https://openalex.org/W3216119459","https://openalex.org/W2786391746","https://openalex.org/W3132346564","https://openalex.org/W4381430104","https://openalex.org/W4226059458","https://openalex.org/W2914559142","https://openalex.org/W2995102745","https://openalex.org/W1990237101"],"abstract_inverted_index":{"In":[0,48],"practice,":[1],"there":[2],"are":[3,24,73],"a":[4,41,84],"variety":[5],"of":[6,16,37,56,86,118,136,157],"real-world":[7],"datasets":[8,23],"that":[9,72,89,132],"have":[10,62,90],"an":[11],"imbalanced":[12,113],"nature":[13,36],"where":[14],"one":[15],"two":[17],"classes":[18],"dominates":[19],"the":[20,34,38,45,103,133,149],"data.":[21],"These":[22],"generally":[25],"difficult":[26],"to":[27,50,67,83,101,126],"classify":[28],"using":[29],"machine":[30],"learning":[31],"algorithms":[32,143],"as":[33,124,138],"skewed":[35],"data":[39,70],"has":[40],"significant":[42],"impact":[43],"on":[44],"training":[46],"process.":[47],"order":[49,66,100],"combat":[51],"this":[52],"difficulty,":[53],"many":[54],"methods":[55],"under":[57],"sampling":[58,61],"and":[59,96],"over":[60,148],"been":[63,91],"proposed":[64],"in":[65,99,146,155],"generate":[68],"comparable":[69],"sets":[71],"more":[74,152],"easily":[75],"classifiable.":[76],"This":[77,109],"study":[78],"applies":[79],"multiple":[80,94],"resampling":[81,137],"techniques":[82],"set":[85],"commit":[87,120],"messages":[88,121],"extracted":[92],"from":[93],"Github":[95],"Sourceforge":[97],"projects":[98],"answer":[102],"question,":[104],"\u201cDo":[105],"developers":[106],"discuss":[107],"design?\u201d":[108],"dataset":[110],"is":[111],"highly":[112],"with":[114,128,140],"less":[115],"than":[116,153],"15%":[117],"all":[119],"being":[122],"classified":[123],"having":[125],"do":[127],"design.":[129],"Results":[130],"demonstrate":[131],"combined":[134],"use":[135],"coupled":[139],"various":[141],"classification":[142,147],"yields":[144],"improvements":[145],"state-of-the-art":[150],"by":[151],"10%":[154],"terms":[156],"accuracy.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}