{"id":"https://openalex.org/W4392157755","doi":"https://doi.org/10.1145/3649596","title":"Data Complexity: A New Perspective for Analyzing the Difficulty of Defect Prediction Tasks","display_name":"Data Complexity: A New Perspective for Analyzing the Difficulty of Defect Prediction Tasks","publication_year":2024,"publication_date":"2024-02-26","ids":{"openalex":"https://openalex.org/W4392157755","doi":"https://doi.org/10.1145/3649596"},"language":"en","primary_location":{"id":"doi:10.1145/3649596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649596","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649596","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3649596","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091107012","display_name":"Xiaohui Wan","orcid":"https://orcid.org/0000-0001-6498-8570"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaohui Wan","raw_affiliation_strings":["Beihang University, Beijing, China","School of Automation Science and Electrical Engineering Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Automation Science and Electrical Engineering Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100459073","display_name":"Zheng Zheng","orcid":"https://orcid.org/0000-0001-7922-9067"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Zheng","raw_affiliation_strings":["Beihang University, Beijing, China","School of Automation Science and Electrical Engineering Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Automation Science and Electrical Engineering Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072209187","display_name":"Fangyun Qin","orcid":"https://orcid.org/0000-0002-3407-5161"},"institutions":[{"id":"https://openalex.org/I96852419","display_name":"Capital Normal University","ror":"https://ror.org/005edt527","country_code":"CN","type":"education","lineage":["https://openalex.org/I96852419"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangyun Qin","raw_affiliation_strings":["Capital Normal University, Beijing, China","College of Information Engineering Capital Normal University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]},{"raw_affiliation_string":"College of Information Engineering Capital Normal University, Beijing, China","institution_ids":["https://openalex.org/I96852419"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016581367","display_name":"Xuhui Lu","orcid":"https://orcid.org/0000-0001-6839-5633"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuhui Lu","raw_affiliation_strings":["Beihang University, Beijing, China","School of Automation Science and Electrical Engineering Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Automation Science and Electrical Engineering Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091107012"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":4.5615,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.94608501,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"33","issue":"6","first_page":"1","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9857000112533569,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/computer-science","display_name":"Computer science","score":0.8060207366943359},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.6843249797821045},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.43990594148635864},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34329336881637573},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3255124092102051}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8060207366943359},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6843249797821045},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.43990594148635864},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34329336881637573},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3255124092102051}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649596","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649596","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3649596","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3649596","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3649596","source":{"id":"https://openalex.org/S142627899","display_name":"ACM Transactions on Software Engineering and Methodology","issn_l":"1049-331X","issn":["1049-331X","1557-7392"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Software Engineering and Methodology","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G1100003544","display_name":null,"funder_award_id":"62372021","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1231421488","display_name":null,"funder_award_id":"under","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5994120800","display_name":null,"funder_award_id":"Natural","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4392157755.pdf","grobid_xml":"https://content.openalex.org/works/W4392157755.grobid-xml"},"referenced_works_count":96,"referenced_works":["https://openalex.org/W830456971","https://openalex.org/W1495180973","https://openalex.org/W1530293531","https://openalex.org/W1537525296","https://openalex.org/W1873332500","https://openalex.org/W1988844742","https://openalex.org/W1992331847","https://openalex.org/W1993220166","https://openalex.org/W2000908325","https://openalex.org/W2004710424","https://openalex.org/W2017439596","https://openalex.org/W2022477494","https://openalex.org/W2025700486","https://openalex.org/W2033398965","https://openalex.org/W2050496630","https://openalex.org/W2063365570","https://openalex.org/W2068430427","https://openalex.org/W2078483536","https://openalex.org/W2097883090","https://openalex.org/W2100483895","https://openalex.org/W2101227285","https://openalex.org/W2105300539","https://openalex.org/W2106525014","https://openalex.org/W2118978333","https://openalex.org/W2125877832","https://openalex.org/W2135198476","https://openalex.org/W2136256517","https://openalex.org/W2143637886","https://openalex.org/W2148143831","https://openalex.org/W2150874999","https://openalex.org/W2150954665","https://openalex.org/W2151666086","https://openalex.org/W2158640358","https://openalex.org/W2158744032","https://openalex.org/W2163732854","https://openalex.org/W2169637438","https://openalex.org/W2260771218","https://openalex.org/W2324349273","https://openalex.org/W2344072768","https://openalex.org/W2360967250","https://openalex.org/W2367798545","https://openalex.org/W2394841101","https://openalex.org/W2424693453","https://openalex.org/W2506187570","https://openalex.org/W2521200999","https://openalex.org/W2560646185","https://openalex.org/W2731743750","https://openalex.org/W2731935965","https://openalex.org/W2765779758","https://openalex.org/W2774137886","https://openalex.org/W2783324346","https://openalex.org/W2791812915","https://openalex.org/W2795013017","https://openalex.org/W2801451195","https://openalex.org/W2807807495","https://openalex.org/W2884770024","https://openalex.org/W2885260234","https://openalex.org/W2889972424","https://openalex.org/W2898435572","https://openalex.org/W2907470663","https://openalex.org/W2911270308","https://openalex.org/W2912744352","https://openalex.org/W2916113523","https://openalex.org/W2963520355","https://openalex.org/W2963548617","https://openalex.org/W2973136425","https://openalex.org/W2985783697","https://openalex.org/W2997591727","https://openalex.org/W3002360338","https://openalex.org/W3009290003","https://openalex.org/W3021475922","https://openalex.org/W3091176757","https://openalex.org/W3091590903","https://openalex.org/W3096328115","https://openalex.org/W3101335903","https://openalex.org/W3119288445","https://openalex.org/W3141989311","https://openalex.org/W3162356827","https://openalex.org/W4206600618","https://openalex.org/W4220717373","https://openalex.org/W4226082918","https://openalex.org/W4232478844","https://openalex.org/W4238859253","https://openalex.org/W4239863959","https://openalex.org/W4245807786","https://openalex.org/W4250023757","https://openalex.org/W4283071628","https://openalex.org/W4283318985","https://openalex.org/W4285490379","https://openalex.org/W4293713156","https://openalex.org/W4310064572","https://openalex.org/W4313142332","https://openalex.org/W4385740286","https://openalex.org/W4402843978","https://openalex.org/W6605110569","https://openalex.org/W6754210197"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Defect":[0],"prediction":[1,26,180,192],"is":[2,104,126],"crucial":[3,173],"for":[4,148,187],"software":[5],"quality":[6],"assurance":[7],"and":[8,28,72,111,118,131,182],"has":[9],"been":[10],"extensively":[11],"researched":[12],"over":[13,57],"recent":[14],"decades.":[15],"However,":[16],"prior":[17],"studies":[18],"rarely":[19],"focus":[20],"on":[21,31],"data":[22,42,137,153,176],"complexity":[23,141,154,177],"in":[24,85,178,190],"defect":[25,76,179,191],"tasks,":[27,181],"even":[29],"less":[30],"understanding":[32],"the":[33,39,54,67,73,93,105,157,172],"difficulties":[34],"of":[35,41,56,63,70,75,175],"these":[36],"tasks":[37],"from":[38],"perspective":[40,186],"complexity.":[43],"In":[44,166],"this":[45,168],"article,":[46],"we":[47],"conduct":[48],"an":[49,162],"empirical":[50,169],"study":[51,170],"to":[52,65,128],"estimate":[53],"hardness":[55,84,110],"33,000":[58],"instances,":[59],"employing":[60],"a":[61,89,97,184],"set":[62],"measures":[64,142],"characterize":[66],"inherent":[68],"difficulty":[69],"instances":[71],"characteristics":[74],"datasets.":[77],"Our":[78],"findings":[79],"indicate":[80],"that:":[81],"(1)":[82],"instance":[83,109],"both":[86],"classes":[87],"displays":[88],"right-skewed":[90],"distribution,":[91],"with":[92],"defective":[94],"class":[95,102],"exhibiting":[96],"more":[98],"scattered":[99],"distribution;":[100],"(2)":[101],"overlap":[103],"primary":[106],"factor":[107],"influencing":[108],"can":[112,143,160],"be":[113],"characterized":[114],"through":[115],"feature,":[116],"structural,":[117],"instance-level":[119],"overlap;":[120],"(3)":[121],"no":[122],"universal":[123],"preprocessing":[124],"technique":[125],"applicable":[127],"all":[129],"datasets,":[130],"it":[132],"may":[133],"not":[134],"consistently":[135],"reduce":[136],"complexity,":[138],"fortunately,":[139],"dataset":[140],"help":[144],"identify":[145],"suitable":[146],"techniques":[147],"specific":[149],"datasets;":[150],"(4)":[151],"integrating":[152],"information":[155],"into":[156],"learning":[158,164],"process":[159],"enhance":[161],"algorithm\u2019s":[163],"capacity.":[165],"summary,":[167],"highlights":[171],"role":[174],"provides":[183],"novel":[185],"advancing":[188],"research":[189],"techniques.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}