{"id":"https://openalex.org/W3199693282","doi":"https://doi.org/10.1109/tse.2022.3171202","title":"Data Preparation for Software Vulnerability Prediction: A Systematic Literature Review","display_name":"Data Preparation for Software Vulnerability Prediction: A Systematic Literature Review","publication_year":2022,"publication_date":"2022-04-28","ids":{"openalex":"https://openalex.org/W3199693282","doi":"https://doi.org/10.1109/tse.2022.3171202","mag":"3199693282"},"language":"en","primary_location":{"id":"doi:10.1109/tse.2022.3171202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2022.3171202","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},"type":"review","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/A5040400519","display_name":"Roland Croft","orcid":"https://orcid.org/0000-0001-5011-6587"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Roland Croft","raw_affiliation_strings":["Centre for Research on Engineering Software Technologies (CREST), School of Computer Science, University of Adelaide, Adelaide, Australia","Cyber Security Cooperative Research Centre, Joondalup, WA, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5011-6587","affiliations":[{"raw_affiliation_string":"Centre for Research on Engineering Software Technologies (CREST), School of Computer Science, University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"Cyber Security Cooperative Research Centre, Joondalup, WA, Australia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018618997","display_name":"Yongzheng Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Yongzheng Xie","raw_affiliation_strings":["Centre for Research on Engineering Software Technologies (CREST), School of Computer Science, University of Adelaide, Adelaide, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Research on Engineering Software Technologies (CREST), School of Computer Science, University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103075476","display_name":"Muhammad Ali Babar","orcid":"https://orcid.org/0000-0001-9696-3626"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Muhammad Ali Babar","raw_affiliation_strings":["Centre for Research on Engineering Software Technologies (CREST), School of Computer Science, University of Adelaide, Adelaide, Australia","Cyber Security Cooperative Research Centre, Joondalup, WA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Research on Engineering Software Technologies (CREST), School of Computer Science, University of Adelaide, Adelaide, Australia","institution_ids":["https://openalex.org/I5681781"]},{"raw_affiliation_string":"Cyber Security Cooperative Research Centre, Joondalup, WA, Australia","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5681781"],"apc_list":null,"apc_paid":null,"fwci":5.2319,"has_fulltext":false,"cited_by_count":63,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"49","issue":"3","first_page":"1044","last_page":"1063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T12423","display_name":"Software Reliability and Analysis Research","score":0.9998000264167786,"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/T10260","display_name":"Software Engineering Research","score":0.9997000098228455,"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/T12127","display_name":"Software System Performance and Reliability","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.7640672326087952},{"id":"https://openalex.org/keywords/systematic-review","display_name":"Systematic review","score":0.6390916109085083},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5785253643989563},{"id":"https://openalex.org/keywords/software-quality-assurance","display_name":"Software quality assurance","score":0.5432857275009155},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.5293415784835815},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5283454060554504},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.47476816177368164},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.4430179297924042},{"id":"https://openalex.org/keywords/quality-assurance","display_name":"Quality assurance","score":0.42778512835502625},{"id":"https://openalex.org/keywords/software-quality","display_name":"Software quality","score":0.326240211725235},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.28458064794540405},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.12282559275627136},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.11895942687988281},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10105901956558228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640672326087952},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.6390916109085083},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5785253643989563},{"id":"https://openalex.org/C2776969324","wikidata":"https://www.wikidata.org/wiki/Q613918","display_name":"Software quality assurance","level":5,"score":0.5432857275009155},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.5293415784835815},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5283454060554504},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.47476816177368164},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.4430179297924042},{"id":"https://openalex.org/C106436119","wikidata":"https://www.wikidata.org/wiki/Q836575","display_name":"Quality assurance","level":3,"score":0.42778512835502625},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.326240211725235},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.28458064794540405},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.12282559275627136},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11895942687988281},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10105901956558228},{"id":"https://openalex.org/C2778618615","wikidata":"https://www.wikidata.org/wiki/Q4008393","display_name":"External quality assessment","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2022.3171202","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2022.3171202","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6000000238418579,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":65,"referenced_works":["https://openalex.org/W54655540","https://openalex.org/W203932818","https://openalex.org/W1567491469","https://openalex.org/W1607167266","https://openalex.org/W1969733464","https://openalex.org/W1975675278","https://openalex.org/W1997236144","https://openalex.org/W1997646511","https://openalex.org/W2009415795","https://openalex.org/W2015232149","https://openalex.org/W2048899404","https://openalex.org/W2067148378","https://openalex.org/W2093897789","https://openalex.org/W2101227285","https://openalex.org/W2111722073","https://openalex.org/W2117366235","https://openalex.org/W2118978333","https://openalex.org/W2122777273","https://openalex.org/W2129083809","https://openalex.org/W2133933998","https://openalex.org/W2135841285","https://openalex.org/W2151666086","https://openalex.org/W2154398797","https://openalex.org/W2161336914","https://openalex.org/W2165394871","https://openalex.org/W2166336492","https://openalex.org/W2168894761","https://openalex.org/W2357329924","https://openalex.org/W2404987555","https://openalex.org/W2494902551","https://openalex.org/W2601947690","https://openalex.org/W2606150376","https://openalex.org/W2613159689","https://openalex.org/W2682463074","https://openalex.org/W2748690817","https://openalex.org/W2766521509","https://openalex.org/W2922234936","https://openalex.org/W2945281596","https://openalex.org/W2953482317","https://openalex.org/W2963725499","https://openalex.org/W2967556797","https://openalex.org/W3008381189","https://openalex.org/W3009517030","https://openalex.org/W3011056055","https://openalex.org/W3015200424","https://openalex.org/W3033777149","https://openalex.org/W3039175093","https://openalex.org/W3081792418","https://openalex.org/W3090988470","https://openalex.org/W3097867666","https://openalex.org/W3108563174","https://openalex.org/W3127782461","https://openalex.org/W3147362533","https://openalex.org/W3149255455","https://openalex.org/W3161804663","https://openalex.org/W3163206498","https://openalex.org/W3166095789","https://openalex.org/W3184339106","https://openalex.org/W3196424583","https://openalex.org/W3202871865","https://openalex.org/W3212368439","https://openalex.org/W4243379839","https://openalex.org/W6608286391","https://openalex.org/W6684456340","https://openalex.org/W6777446418"],"related_works":["https://openalex.org/W4248404226","https://openalex.org/W2169893063","https://openalex.org/W2538046782","https://openalex.org/W1580492598","https://openalex.org/W1822997579","https://openalex.org/W2994240680","https://openalex.org/W2017337427","https://openalex.org/W2549211027","https://openalex.org/W2538047245","https://openalex.org/W2504378244"],"abstract_inverted_index":{"Software":[0,20,29],"Vulnerability":[1,30],"Prediction":[2],"(SVP)":[3],"is":[4,34,56],"a":[5,83,95,122,165],"data-driven":[6],"technique":[7],"for":[8,127,158,169],"software":[9],"quality":[10],"assurance":[11],"that":[12],"has":[13,117,152],"recently":[14],"gained":[15],"considerable":[16],"attention":[17],"in":[18,91],"the":[19,25,37,47,66,71,101,107,113,134,141,147,150,156],"Engineering":[21],"research":[22,90],"community.":[23],"However,":[24],"difficulties":[26],"of":[27,43,88,98,100,112,124,146,149,167,173],"preparing":[28],"(SV)":[31],"related":[32,129],"data":[33,74,102,125],"considered":[35],"as":[36],"main":[38],"barrier":[39],"to":[40,60,93,120],"industrial":[41],"adoption":[42],"SVP":[44,89,128,174],"approaches.":[45,175],"Given":[46],"increasing,":[48],"but":[49],"dispersed,":[50],"literature":[51],"on":[52],"this":[53],"topic,":[54],"it":[55],"needed":[57,108],"and":[58,64,77,106,137,171],"timely":[59],"systematically":[61],"select,":[62],"review,":[63],"synthesize":[65],"relevant":[67,115],"peer-reviewed":[68],"papers":[69,116],"reporting":[70],"existing":[72],"SV":[73],"preparation":[75,103,126],"techniques":[76],"challenges.":[78,130],"We":[79,131],"have":[80,132],"carried":[81],"out":[82],"Systematic":[84],"Literature":[85],"Review":[86],"(SLR)":[87],"order":[92],"develop":[94,121],"systematized":[96],"body":[97],"knowledge":[99],"challenges,":[104],"solutions,":[105],"research.":[109,160],"Our":[110,144],"review":[111,162],"61":[114],"enabled":[118,153],"us":[119,154],"taxonomy":[123],"analyzed":[133],"identified":[135],"challenges":[136],"available":[138],"solutions":[139],"using":[140],"proposed":[142],"taxonomy.":[143],"analysis":[145],"state":[148],"art":[151],"identify":[155],"opportunities":[157],"future":[159],"This":[161],"also":[163],"provides":[164],"set":[166],"recommendations":[168],"researchers":[170],"practitioners":[172]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":21},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}