{"id":"https://openalex.org/W2968919339","doi":"https://doi.org/10.1145/3340482.3342744","title":"On the role of data balancing for machine learning-based code smell detection","display_name":"On the role of data balancing for machine learning-based code smell detection","publication_year":2019,"publication_date":"2019-08-08","ids":{"openalex":"https://openalex.org/W2968919339","doi":"https://doi.org/10.1145/3340482.3342744","mag":"2968919339"},"language":"en","primary_location":{"id":"doi:10.1145/3340482.3342744","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340482.3342744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM SIGSOFT International Workshop on Machine Learning Techniques for Software Quality Evaluation","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/A5021041082","display_name":"Fabiano Pecorelli","orcid":"https://orcid.org/0000-0003-2446-4291"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Fabiano Pecorelli","raw_affiliation_strings":["University of Salerno, Italy"],"affiliations":[{"raw_affiliation_string":"University of Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072127726","display_name":"Dario Di Nucci","orcid":"https://orcid.org/0000-0002-3861-1902"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Dario Di Nucci","raw_affiliation_strings":["Vrije Universiteit Brussel, Belgium"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042827940","display_name":"Coen De Roover","orcid":"https://orcid.org/0000-0002-1710-1268"},"institutions":[{"id":"https://openalex.org/I13469542","display_name":"Vrije Universiteit Brussel","ror":"https://ror.org/006e5kg04","country_code":"BE","type":"education","lineage":["https://openalex.org/I13469542"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Coen De Roover","raw_affiliation_strings":["Vrije Universiteit Brussel, Belgium"],"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Brussel, Belgium","institution_ids":["https://openalex.org/I13469542"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079088548","display_name":"Andrea De Lucia","orcid":"https://orcid.org/0000-0002-4238-1425"},"institutions":[{"id":"https://openalex.org/I131729948","display_name":"University of Salerno","ror":"https://ror.org/0192m2k53","country_code":"IT","type":"education","lineage":["https://openalex.org/I131729948"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea De Lucia","raw_affiliation_strings":["University of Salerno, Italy"],"affiliations":[{"raw_affiliation_string":"University of Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021041082"],"corresponding_institution_ids":["https://openalex.org/I131729948"],"apc_list":null,"apc_paid":null,"fwci":7.1222,"has_fulltext":false,"cited_by_count":56,"citation_normalized_percentile":{"value":0.9709662,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"19","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"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":0.9998999834060669,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.989799976348877,"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"}},{"id":"https://openalex.org/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9782000184059143,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/code-smell","display_name":"Code smell","score":0.907140851020813},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8349002599716187},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.639711856842041},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6060210466384888},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.5994938015937805},{"id":"https://openalex.org/keywords/dependability","display_name":"Dependability","score":0.5787488222122192},{"id":"https://openalex.org/keywords/code-review","display_name":"Code review","score":0.5626428723335266},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.5595645904541016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5459808111190796},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4687049090862274},{"id":"https://openalex.org/keywords/technical-debt","display_name":"Technical debt","score":0.44500988721847534},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4332849085330963},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3340374231338501},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.30256715416908264},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.24788284301757812},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16598021984100342}],"concepts":[{"id":"https://openalex.org/C133237599","wikidata":"https://www.wikidata.org/wiki/Q2295111","display_name":"Code smell","level":5,"score":0.907140851020813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8349002599716187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.639711856842041},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6060210466384888},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5994938015937805},{"id":"https://openalex.org/C77019957","wikidata":"https://www.wikidata.org/wiki/Q2689057","display_name":"Dependability","level":2,"score":0.5787488222122192},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.5626428723335266},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.5595645904541016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5459808111190796},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4687049090862274},{"id":"https://openalex.org/C159198006","wikidata":"https://www.wikidata.org/wiki/Q1532172","display_name":"Technical debt","level":4,"score":0.44500988721847534},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4332849085330963},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3340374231338501},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.30256715416908264},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.24788284301757812},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16598021984100342},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3340482.3342744","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3340482.3342744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd ACM SIGSOFT International Workshop on Machine Learning Techniques for Software Quality Evaluation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W46659105","https://openalex.org/W121890015","https://openalex.org/W169052826","https://openalex.org/W649920412","https://openalex.org/W1483313504","https://openalex.org/W1495061682","https://openalex.org/W1500690868","https://openalex.org/W1550696814","https://openalex.org/W1660390307","https://openalex.org/W1912123407","https://openalex.org/W1963598945","https://openalex.org/W1964962870","https://openalex.org/W1970029789","https://openalex.org/W1974655094","https://openalex.org/W1986136726","https://openalex.org/W1991172342","https://openalex.org/W2001730430","https://openalex.org/W2014216297","https://openalex.org/W2034400602","https://openalex.org/W2073792498","https://openalex.org/W2076804800","https://openalex.org/W2087450238","https://openalex.org/W2097998348","https://openalex.org/W2100925270","https://openalex.org/W2112081648","https://openalex.org/W2119811370","https://openalex.org/W2128581098","https://openalex.org/W2130509252","https://openalex.org/W2133990480","https://openalex.org/W2140504739","https://openalex.org/W2148143831","https://openalex.org/W2151295763","https://openalex.org/W2153887189","https://openalex.org/W2170860398","https://openalex.org/W2216905672","https://openalex.org/W2245188050","https://openalex.org/W2402199355","https://openalex.org/W2403793401","https://openalex.org/W2508117657","https://openalex.org/W2576115447","https://openalex.org/W2608628736","https://openalex.org/W2742512005","https://openalex.org/W2752705533","https://openalex.org/W2767787791","https://openalex.org/W2787379525","https://openalex.org/W2789476037","https://openalex.org/W2796404405","https://openalex.org/W2900538539","https://openalex.org/W2908058835","https://openalex.org/W2918249627","https://openalex.org/W2954327103","https://openalex.org/W2968919339","https://openalex.org/W2998678832","https://openalex.org/W4287643567","https://openalex.org/W6606879723","https://openalex.org/W6674385629","https://openalex.org/W6683106902","https://openalex.org/W6921078687"],"related_works":["https://openalex.org/W4287262327","https://openalex.org/W2014216297","https://openalex.org/W4241437391","https://openalex.org/W3177447400","https://openalex.org/W4254993176","https://openalex.org/W3128257033","https://openalex.org/W3136205849","https://openalex.org/W2147863284","https://openalex.org/W3127057638","https://openalex.org/W3216559261"],"abstract_inverted_index":{"Code":[0],"smells":[1],"can":[2,82],"compromise":[3],"software":[4],"quality":[5],"in":[6,28,39,160],"the":[7,29,111,116,155],"long":[8],"term":[9],"by":[10],"inducing":[11],"technical":[12],"debt.":[13],"For":[14],"this":[15,119],"reason,":[16],"many":[17],"approaches":[18,124,137],"aimed":[19],"at":[20],"identifying":[21],"these":[22,58,73],"design":[23],"flaws":[24],"have":[25],"been":[26],"proposed":[27],"last":[30],"decade.":[31],"Most":[32],"of":[33,43,61,115,147,157],"them":[34],"are":[35],"based":[36],"on":[37,135],"heuristics":[38],"which":[40],"a":[41,145],"set":[42],"metrics":[44],"(e.g.,":[45],"code":[46,55,106,139,162],"metrics,":[47],"process":[48],"metrics)":[49],"is":[50,101],"used":[51],"to":[52,110,126,131,154],"detect":[53],"smelly":[54],"components.":[56],"However,":[57,92],"techniques":[59,80],"suffer":[60],"subjective":[62],"interpretation,":[63],"low":[64],"agreement":[65],"between":[66],"detectors,":[67],"and":[68,149],"threshold":[69,90],"dependability.":[70],"To":[71],"overcome":[72],"limitations,":[74],"previous":[75,85],"work":[76,95],"applied":[77],"Machine":[78,99],"Learning":[79,100],"that":[81,98],"learn":[83],"from":[84],"datasets":[86],"without":[87],"needing":[88],"any":[89],"definition.":[91],"more":[93],"recent":[94],"has":[96],"shown":[97],"not":[102],"always":[103],"suitable":[104],"for":[105,138],"smell":[107,140,163],"detection":[108],"due":[109],"highly":[112],"unbalanced":[113],"nature":[114],"problem.":[117],"In":[118],"study":[120],"we":[121],"investigate":[122],"several":[123],"able":[125],"mitigate":[127],"data":[128,158],"unbalancing":[129],"issues":[130,151],"understand":[132],"their":[133],"impact":[134],"ML-based":[136,161],"detection.":[141,164],"Our":[142],"findings":[143],"highlight":[144],"number":[146],"limitations":[148],"open":[150],"with":[152],"respect":[153],"usage":[156],"balancing":[159]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}