{"id":"https://openalex.org/W4376505268","doi":"https://doi.org/10.1145/3596908","title":"A Systematic Literature Review on the Code Smells Datasets and Validation Mechanisms","display_name":"A Systematic Literature Review on the Code Smells Datasets and Validation Mechanisms","publication_year":2023,"publication_date":"2023-05-13","ids":{"openalex":"https://openalex.org/W4376505268","doi":"https://doi.org/10.1145/3596908"},"language":"en","primary_location":{"id":"doi:10.1145/3596908","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3596908","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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 Computing Surveys","raw_type":"journal-article"},"type":"review","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2306.01377","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082234429","display_name":"Morteza Zakeri\u2010Nasrabadi","orcid":"https://orcid.org/0000-0003-4289-0606"},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Morteza Zakeri-Nasrabadi","raw_affiliation_strings":["School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0003-4289-0606","affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039758530","display_name":"Saeed Parsa","orcid":"https://orcid.org/0000-0003-4381-2773"},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Saeed Parsa","raw_affiliation_strings":["School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0003-4381-2773","affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101831554","display_name":"Ehsan Esmaili","orcid":"https://orcid.org/0000-0002-3522-5002"},"institutions":[{"id":"https://openalex.org/I67009956","display_name":"Iran University of Science and Technology","ror":"https://ror.org/01jw2p796","country_code":"IR","type":"education","lineage":["https://openalex.org/I67009956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ehsan Esmaili","raw_affiliation_strings":["School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran"],"raw_orcid":"https://orcid.org/0000-0002-3522-5002","affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran","institution_ids":["https://openalex.org/I67009956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033738898","display_name":"Fabio Palomba","orcid":"https://orcid.org/0000-0001-9337-5116"},"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":"Fabio Palomba","raw_affiliation_strings":["Department of Computer Science, University of Salerno, Salerno, Italy"],"raw_orcid":"https://orcid.org/0000-0001-9337-5116","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Salerno, Salerno, Italy","institution_ids":["https://openalex.org/I131729948"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6701,"has_fulltext":true,"cited_by_count":38,"citation_normalized_percentile":{"value":0.88668867,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"55","issue":"13s","first_page":"1","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":1.0,"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":1.0,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.998199999332428,"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"}},{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9948999881744385,"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/code-smell","display_name":"Code smell","score":0.9437851905822754},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.85801100730896},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.585842490196228},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.5764248371124268},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4161970615386963},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.40985316038131714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3942820429801941},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33986377716064453},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.1565522849559784},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1339227557182312},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.12868714332580566},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.11849448084831238},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.07670173048973083}],"concepts":[{"id":"https://openalex.org/C133237599","wikidata":"https://www.wikidata.org/wiki/Q2295111","display_name":"Code smell","level":5,"score":0.9437851905822754},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.85801100730896},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.585842490196228},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5764248371124268},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4161970615386963},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.40985316038131714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3942820429801941},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33986377716064453},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.1565522849559784},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1339227557182312},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.12868714332580566},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.11849448084831238},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.07670173048973083}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3596908","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3596908","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"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 Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2306.01377","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.01377","pdf_url":"https://arxiv.org/pdf/2306.01377","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2306.01377","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.01377","pdf_url":"https://arxiv.org/pdf/2306.01377","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4376505268.pdf","grobid_xml":"https://content.openalex.org/works/W4376505268.grobid-xml"},"referenced_works_count":107,"referenced_works":["https://openalex.org/W144610867","https://openalex.org/W649920412","https://openalex.org/W1709483371","https://openalex.org/W1970029789","https://openalex.org/W1970210446","https://openalex.org/W1975675278","https://openalex.org/W1978777139","https://openalex.org/W1986136726","https://openalex.org/W1988997230","https://openalex.org/W1991172342","https://openalex.org/W2006027584","https://openalex.org/W2027203221","https://openalex.org/W2032860265","https://openalex.org/W2034400602","https://openalex.org/W2038214150","https://openalex.org/W2060561050","https://openalex.org/W2068011713","https://openalex.org/W2068321882","https://openalex.org/W2071983648","https://openalex.org/W2087450238","https://openalex.org/W2095938258","https://openalex.org/W2100925270","https://openalex.org/W2103134547","https://openalex.org/W2113322762","https://openalex.org/W2134203992","https://openalex.org/W2136224168","https://openalex.org/W2139074146","https://openalex.org/W2139851189","https://openalex.org/W2144854572","https://openalex.org/W2151295763","https://openalex.org/W2153365511","https://openalex.org/W2158864412","https://openalex.org/W2166492919","https://openalex.org/W2167363007","https://openalex.org/W2170860398","https://openalex.org/W2200427962","https://openalex.org/W2213051614","https://openalex.org/W2245188050","https://openalex.org/W2277619875","https://openalex.org/W2290314319","https://openalex.org/W2296719434","https://openalex.org/W2402199355","https://openalex.org/W2403793401","https://openalex.org/W2472384644","https://openalex.org/W2565457067","https://openalex.org/W2571223783","https://openalex.org/W2593156329","https://openalex.org/W2596214868","https://openalex.org/W2605547445","https://openalex.org/W2608628736","https://openalex.org/W2617348763","https://openalex.org/W2620223397","https://openalex.org/W2742512005","https://openalex.org/W2751180361","https://openalex.org/W2772484800","https://openalex.org/W2780783514","https://openalex.org/W2787379525","https://openalex.org/W2789476037","https://openalex.org/W2794185179","https://openalex.org/W2795868997","https://openalex.org/W2796404405","https://openalex.org/W2799758613","https://openalex.org/W2804191478","https://openalex.org/W2809258218","https://openalex.org/W2888728157","https://openalex.org/W2899407111","https://openalex.org/W2900538539","https://openalex.org/W2902324490","https://openalex.org/W2908058835","https://openalex.org/W2911964244","https://openalex.org/W2919418334","https://openalex.org/W2954327103","https://openalex.org/W2956390618","https://openalex.org/W2963197901","https://openalex.org/W2965526865","https://openalex.org/W2969368867","https://openalex.org/W2990340259","https://openalex.org/W2994767694","https://openalex.org/W2998214346","https://openalex.org/W2998318846","https://openalex.org/W3014553393","https://openalex.org/W3020617474","https://openalex.org/W3020936518","https://openalex.org/W3034060521","https://openalex.org/W3035156651","https://openalex.org/W3080350722","https://openalex.org/W3083887248","https://openalex.org/W3088620338","https://openalex.org/W3089328932","https://openalex.org/W3089863335","https://openalex.org/W3100183864","https://openalex.org/W3104802707","https://openalex.org/W3113486250","https://openalex.org/W3119696503","https://openalex.org/W3122864121","https://openalex.org/W3162040020","https://openalex.org/W3208869604","https://openalex.org/W4205607617","https://openalex.org/W4220864612","https://openalex.org/W4243311255","https://openalex.org/W4249489731","https://openalex.org/W4253091331","https://openalex.org/W4254182148","https://openalex.org/W4292622331","https://openalex.org/W4292845462","https://openalex.org/W4393457445","https://openalex.org/W6950367199"],"related_works":["https://openalex.org/W3134933787","https://openalex.org/W3116338676","https://openalex.org/W2786648929","https://openalex.org/W2774816643","https://openalex.org/W4286793953","https://openalex.org/W2806610047","https://openalex.org/W2031808517","https://openalex.org/W2950234014","https://openalex.org/W4205203654","https://openalex.org/W2809258218"],"abstract_inverted_index":{"The":[0],"accuracy":[1],"reported":[2],"for":[3,30],"code":[4],"smell-detecting":[5],"tools":[6],"varies":[7],"depending":[8],"on":[9,35],"the":[10,15,25,40,56,64],"dataset":[11,29],"used":[12],"to":[13,60,107],"evaluate":[14],"tools.":[16],"Our":[17],"survey":[18],"of":[19,27,47,50,53,58,101],"45":[20],"existing":[21,67,94],"datasets":[22,68,95],"reveals":[23],"that":[24,93],"adequacy":[26],"a":[28],"detecting":[31],"smells":[32,79],"highly":[33],"depends":[34],"relevant":[36],"properties":[37],"such":[38],"as":[39],"size,":[41],"severity":[42,103],"level,":[43,104],"project":[44],"types,":[45],"number":[46,52],"each":[48],"type":[49],"smell,":[51],"smells,":[54],"and":[55,74,82,105],"ratio":[57],"smelly":[59],"non-smelly":[61],"samples":[62],"in":[63,80],"dataset.":[65],"Most":[66],"support":[69],"God":[70],"Class,":[71],"Long":[72],"Method,":[73],"Feature":[75],"Envy,":[76],"while":[77],"six":[78],"Fowler":[81],"Beck's":[83],"catalog":[84],"are":[85],"not":[86],"supported":[87],"by":[88],"any":[89],"datasets.":[90],"We":[91],"conclude":[92],"suffer":[96],"from":[97],"imbalanced":[98],"samples,":[99],"lack":[100],"supporting":[102],"restriction":[106],"Java":[108],"language.":[109]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-05-15T00:00:00"}
