{"id":"https://openalex.org/W2126957654","doi":"https://doi.org/10.1145/1390817.1390822","title":"Can data transformation help in the detection of fault-prone modules?","display_name":"Can data transformation help in the detection of fault-prone modules?","publication_year":2008,"publication_date":"2008-07-20","ids":{"openalex":"https://openalex.org/W2126957654","doi":"https://doi.org/10.1145/1390817.1390822","mag":"2126957654"},"language":"en","primary_location":{"id":"doi:10.1145/1390817.1390822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390817.1390822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 workshop on Defects in large software systems","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/A5063124087","display_name":"Yue Jiang","orcid":"https://orcid.org/0000-0003-0024-0605"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yue Jiang","raw_affiliation_strings":["West Virginia University, Morgantown, WV"],"affiliations":[{"raw_affiliation_string":"West Virginia University, Morgantown, WV","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015369081","display_name":"Bojan \u010cuki\u0107","orcid":"https://orcid.org/0000-0001-7130-9054"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bojan Cukic","raw_affiliation_strings":["West Virginia University, Morgantown, WV"],"affiliations":[{"raw_affiliation_string":"West Virginia University, Morgantown, WV","institution_ids":["https://openalex.org/I12097938"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077008083","display_name":"Tim Menzies","orcid":"https://orcid.org/0000-0002-5040-3196"},"institutions":[{"id":"https://openalex.org/I12097938","display_name":"West Virginia University","ror":"https://ror.org/011vxgd24","country_code":"US","type":"education","lineage":["https://openalex.org/I12097938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tim Menzies","raw_affiliation_strings":["West Virginia University, Morgantown, WV"],"affiliations":[{"raw_affiliation_string":"West Virginia University, Morgantown, WV","institution_ids":["https://openalex.org/I12097938"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063124087"],"corresponding_institution_ids":["https://openalex.org/I12097938"],"apc_list":null,"apc_paid":null,"fwci":12.2469,"has_fulltext":false,"cited_by_count":103,"citation_normalized_percentile":{"value":0.98283009,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"16","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9972000122070312,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9972000122070312,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9887999892234802,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9767000079154968,"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/preprocessor","display_name":"Preprocessor","score":0.7521688938140869},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.7460329532623291},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7433983683586121},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.7366964817047119},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6950007677078247},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.6555367708206177},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6473400592803955},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6199542284011841},{"id":"https://openalex.org/keywords/data-transformation","display_name":"Data transformation","score":0.494064599275589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4550720751285553},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4505671262741089},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.44036561250686646},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43078097701072693},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4153144657611847},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15011286735534668},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.09440141916275024}],"concepts":[{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.7521688938140869},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.7460329532623291},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7433983683586121},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.7366964817047119},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6950007677078247},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6555367708206177},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6473400592803955},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6199542284011841},{"id":"https://openalex.org/C150670458","wikidata":"https://www.wikidata.org/wiki/Q4272815","display_name":"Data transformation","level":3,"score":0.494064599275589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4550720751285553},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4505671262741089},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.44036561250686646},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43078097701072693},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4153144657611847},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15011286735534668},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.09440141916275024},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1390817.1390822","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1390817.1390822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 workshop on Defects in large software systems","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.352.8435","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.352.8435","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://menzies.us/pdf/08transform.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W53188351","https://openalex.org/W103650626","https://openalex.org/W1565746575","https://openalex.org/W1570448133","https://openalex.org/W1585743408","https://openalex.org/W1678889691","https://openalex.org/W1922017469","https://openalex.org/W2107263745","https://openalex.org/W2138827327","https://openalex.org/W2160958420","https://openalex.org/W2167714234","https://openalex.org/W2911964244","https://openalex.org/W2966207845","https://openalex.org/W3099514962","https://openalex.org/W4302367531","https://openalex.org/W6776535907","https://openalex.org/W6995831674"],"related_works":["https://openalex.org/W2474028989","https://openalex.org/W2989490741","https://openalex.org/W3092506759","https://openalex.org/W2367545121","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513","https://openalex.org/W120741642","https://openalex.org/W2393746579","https://openalex.org/W2952736244"],"abstract_inverted_index":{"Data":[0,34],"preprocessing":[1,23],"(transformation)":[2],"plays":[3],"an":[4],"important":[5],"role":[6],"in":[7],"data":[8,78,99],"mining":[9],"and":[10,37,75,81],"machine":[11],"learning.":[12],"In":[13],"this":[14],"study,":[15],"we":[16],"investigate":[17],"the":[18,54,109],"effect":[19],"of":[20,56,62,111],"four":[21],"different":[22,58,63],"methods":[24],"to":[25,107],"fault-proneness":[26],"prediction":[27],"using":[28],"nine":[29],"datasets":[30],"from":[31,98],"NASA":[32],"Metrics":[33],"Programs":[35],"(MDP)":[36],"ten":[38],"classification":[39,49,113],"algorithms.":[40,59,114],"Our":[41],"experiments":[42],"indicate":[43],"that":[44,91],"log":[45,76],"transformation":[46,103],"rarely":[47],"improves":[48],"performance,":[50],"but":[51],"discretization":[52],"affects":[53],"performance":[55,110],"many":[57],"The":[60],"impact":[61],"transformations":[64],"differs.":[65],"Random":[66],"forest":[67],"algorithm,":[68],"for":[69],"example,":[70],"performs":[71],"better":[72,85],"with":[73,86],"original":[74],"transformed":[77],"set.":[79],"Boosting":[80],"NaiveBayes":[82],"perform":[83],"significantly":[84],"discretized":[87],"data.":[88],"We":[89],"conclude":[90],"no":[92],"general":[93],"benefit":[94],"can":[95],"be":[96],"expected":[97],"transformations.":[100],"Instead,":[101],"selected":[102],"techniques":[104],"are":[105],"recommended":[106],"boost":[108],"specific":[112]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":14},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}