{"id":"https://openalex.org/W4403413397","doi":"https://doi.org/10.1145/3674805.3690747","title":"On the Creation of Representative Samples of Software Repositories","display_name":"On the Creation of Representative Samples of Software Repositories","publication_year":2024,"publication_date":"2024-10-15","ids":{"openalex":"https://openalex.org/W4403413397","doi":"https://doi.org/10.1145/3674805.3690747"},"language":"en","primary_location":{"id":"doi:10.1145/3674805.3690747","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674805.3690747","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3674805.3690747?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3674805.3690747?download=true","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114271587","display_name":"June Gorostidi","orcid":null},"institutions":[{"id":"https://openalex.org/I138847295","display_name":"Universitat Oberta de Catalunya","ror":"https://ror.org/01f5wp925","country_code":"ES","type":"education","lineage":["https://openalex.org/I138847295"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"June Gorostidi","raw_affiliation_strings":["Universitat Oberta de Catalunya (UOC), Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Oberta de Catalunya (UOC), Spain","institution_ids":["https://openalex.org/I138847295"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081900823","display_name":"Adem Ait","orcid":"https://orcid.org/0000-0002-5334-9041"},"institutions":[{"id":"https://openalex.org/I186903577","display_name":"University of Luxembourg","ror":"https://ror.org/036x5ad56","country_code":"LU","type":"education","lineage":["https://openalex.org/I186903577"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Adem Ait","raw_affiliation_strings":["University of Luxembourg, Luxembourg"],"affiliations":[{"raw_affiliation_string":"University of Luxembourg, Luxembourg","institution_ids":["https://openalex.org/I186903577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074872542","display_name":"Jordi Cabot","orcid":"https://orcid.org/0000-0003-2418-2489"},"institutions":[{"id":"https://openalex.org/I4210112527","display_name":"Luxembourg Institute of Science and Technology","ror":"https://ror.org/01t178j62","country_code":"LU","type":"nonprofit","lineage":["https://openalex.org/I4210112527"]}],"countries":["LU"],"is_corresponding":false,"raw_author_name":"Jordi Cabot","raw_affiliation_strings":["Luxembourg Institute of Science and Technology (LIST), Luxembourg"],"affiliations":[{"raw_affiliation_string":"Luxembourg Institute of Science and Technology (LIST), Luxembourg","institution_ids":["https://openalex.org/I4210112527"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011891628","display_name":"Javier Luis Izquierdo","orcid":"https://orcid.org/0000-0002-2326-1700"},"institutions":[{"id":"https://openalex.org/I138847295","display_name":"Universitat Oberta de Catalunya","ror":"https://ror.org/01f5wp925","country_code":"ES","type":"education","lineage":["https://openalex.org/I138847295"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Luis Canovas Izquierdo","raw_affiliation_strings":["Universitat Oberta de Catalunya (UOC), Spain"],"affiliations":[{"raw_affiliation_string":"Universitat Oberta de Catalunya (UOC), Spain","institution_ids":["https://openalex.org/I138847295"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5114271587"],"corresponding_institution_ids":["https://openalex.org/I138847295"],"apc_list":null,"apc_paid":null,"fwci":1.5269,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.8747294,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"434","last_page":"439"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9940000176429749,"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":0.9940000176429749,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9882000088691711,"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/computer-science","display_name":"Computer science","score":0.6367394328117371},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.47689417004585266},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.45593565702438354},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3765505850315094},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.34575822949409485},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14252060651779175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6367394328117371},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.47689417004585266},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.45593565702438354},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3765505850315094},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.34575822949409485},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14252060651779175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3674805.3690747","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674805.3690747","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3674805.3690747?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},{"id":"pmh:oai:orbilu.uni.lu:10993/63516","is_oa":true,"landing_page_url":"https://orbilu.uni.lu/handle/10993/63516","pdf_url":"https://orbilu.uni.lu/bitstream/10993/63516/1/esem24-main.pdf","source":{"id":"https://openalex.org/S4306401815","display_name":"Open Repository and Bibliography (University of Luxembourg)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I186903577","host_organization_name":"University of Luxembourg","host_organization_lineage":["https://openalex.org/I186903577"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement, ESEM 2024 (2024-10-24); Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement, Barcelona, Esp [Esp], 24-10-2024 => 25-10-2024","raw_type":"peer reviewed"}],"best_oa_location":{"id":"doi:10.1145/3674805.3690747","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3674805.3690747","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3674805.3690747?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2262748287","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3480869486","display_name":null,"funder_award_id":"13039","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G3681454997","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4042783231","display_name":null,"funder_award_id":"501100011033","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4126322094","display_name":null,"funder_award_id":"01100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G446383756","display_name":null,"funder_award_id":"16544475","funder_id":"https://openalex.org/F4320321038","funder_display_name":"Fonds National de la Recherche Luxembourg"},{"id":"https://openalex.org/G661330594","display_name":null,"funder_award_id":"00110","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G6685425346","display_name":null,"funder_award_id":"0011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7084143925","display_name":null,"funder_award_id":"AEI/10","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G7266728691","display_name":null,"funder_award_id":"13039/501100011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"},{"id":"https://openalex.org/G8260616629","display_name":null,"funder_award_id":"011033","funder_id":"https://openalex.org/F4320335598","funder_display_name":"Agencia Estatal de Investigaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321038","display_name":"Fonds National de la Recherche Luxembourg","ror":"https://ror.org/039z13y21"},{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403413397.pdf","grobid_xml":"https://content.openalex.org/works/W4403413397.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W2169090130","https://openalex.org/W2404313524","https://openalex.org/W2498260651","https://openalex.org/W2809093041","https://openalex.org/W3006568433","https://openalex.org/W3204368535","https://openalex.org/W4245135410","https://openalex.org/W4299827484","https://openalex.org/W4390707532"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032"],"abstract_inverted_index":{"Software":[0,11,17],"repositories":[1,50,90,158],"is":[2,79,147],"one":[3],"of":[4,7,29,35,48,63,76,99,101,141,154,157,162],"the":[5,15,25,33,89,123,152,155,160,163],"sources":[6],"data":[8,55],"in":[9,14],"Empirical":[10],"Engineering,":[12],"primarily":[13],"Mining":[16],"Repositories":[18],"field,":[19],"aimed":[20],"at":[21],"extracting":[22],"knowledge":[23],"from":[24],"dynamics":[26],"and":[27,83,159],"practice":[28],"software":[30,49,142],"projects.":[31],"With":[32,59],"emergence":[34],"social":[36],"coding":[37],"platforms":[38],"such":[39,145],"as":[40,53],"GitHub,":[41],"researchers":[42,84],"have":[43,85],"now":[44],"access":[45],"to":[46,51,69,86,91,96,122],"millions":[47],"use":[52,171],"source":[54],"for":[56,137],"their":[57],"studies.":[58],"this":[60,131],"massive":[61],"amount":[62],"data,":[64],"sampling":[65,105],"techniques":[66],"are":[67,107],"needed":[68],"create":[70,92],"more":[71],"manageable":[72],"datasets.":[73],"The":[74],"creation":[75],"these":[77],"datasets":[78],"a":[80,97,135],"crucial":[81],"step,":[82],"carefully":[87],"select":[88],"representative":[93,139],"samples":[94,140],"according":[95],"set":[98],"variables":[100,116],"interest.":[102],"However,":[103],"current":[104],"methods":[106],"often":[108],"based":[109,173],"on":[110,115,174],"random":[111],"selection":[112],"or":[113,128],"rely":[114],"which":[117],"may":[118],"not":[119],"be":[120],"related":[121],"research":[124],"study":[125],"(e.g.,":[126],"popularity":[127],"activity).":[129],"In":[130],"paper,":[132],"we":[133],"present":[134],"methodology":[136],"creating":[138],"repositories,":[143],"where":[144],"representativeness":[146],"properly":[148],"aligned":[149],"with":[150,170],"both":[151],"characteristics":[153],"population":[156],"requirements":[161],"empirical":[164],"study.":[165],"We":[166],"illustrate":[167],"our":[168],"approach":[169],"cases":[172],"Hugging":[175],"Face":[176],"repositories.":[177]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2024-10-16T00:00:00"}