{"id":"https://openalex.org/W1985994919","doi":"https://doi.org/10.1109/icsm.2012.6405329","title":"Who's who in Gnome: Using LSA to merge software repository identities","display_name":"Who's who in Gnome: Using LSA to merge software repository identities","publication_year":2012,"publication_date":"2012-09-01","ids":{"openalex":"https://openalex.org/W1985994919","doi":"https://doi.org/10.1109/icsm.2012.6405329","mag":"1985994919"},"language":"en","primary_location":{"id":"doi:10.1109/icsm.2012.6405329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsm.2012.6405329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 28th IEEE International Conference on Software Maintenance (ICSM)","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/A5027088423","display_name":"Erik Kouters","orcid":null},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Erik Kouters","raw_affiliation_strings":["Technische Universiteit Eindhoven, Eindhoven, The Netherlands","Technische Universiteit Eindhoven, Den Dolech 2, P.O. Box 513, 5600 MB Eindhoven, The Netherlands#TAB#"],"affiliations":[{"raw_affiliation_string":"Technische Universiteit Eindhoven, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Technische Universiteit Eindhoven, Den Dolech 2, P.O. Box 513, 5600 MB Eindhoven, The Netherlands#TAB#","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050821883","display_name":"Bogdan Vasilescu","orcid":"https://orcid.org/0000-0003-4418-5783"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Bogdan Vasilescu","raw_affiliation_strings":["Technische Universiteit Eindhoven, Eindhoven, The Netherlands","Technische Universiteit Eindhoven, Den Dolech 2, P.O. Box 513, 5600 MB Eindhoven, The Netherlands#TAB#"],"affiliations":[{"raw_affiliation_string":"Technische Universiteit Eindhoven, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Technische Universiteit Eindhoven, Den Dolech 2, P.O. Box 513, 5600 MB Eindhoven, The Netherlands#TAB#","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054753279","display_name":"Alexander Serebrenik","orcid":"https://orcid.org/0000-0002-1418-0095"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alexander Serebrenik","raw_affiliation_strings":["Technische Universiteit Eindhoven, Eindhoven, The Netherlands","Technische Universiteit Eindhoven, Den Dolech 2, P.O. Box 513, 5600 MB Eindhoven, The Netherlands#TAB#"],"affiliations":[{"raw_affiliation_string":"Technische Universiteit Eindhoven, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Technische Universiteit Eindhoven, Den Dolech 2, P.O. Box 513, 5600 MB Eindhoven, The Netherlands#TAB#","institution_ids":["https://openalex.org/I83019370"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029542014","display_name":"Mark van den Brand","orcid":"https://orcid.org/0000-0003-3529-6182"},"institutions":[{"id":"https://openalex.org/I83019370","display_name":"Eindhoven University of Technology","ror":"https://ror.org/02c2kyt77","country_code":"NL","type":"education","lineage":["https://openalex.org/I83019370"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mark G. J. van den Brand","raw_affiliation_strings":["Technische Universiteit Eindhoven, Eindhoven, The Netherlands","Technische Universiteit Eindhoven, Den Dolech 2, P.O. Box 513, 5600 MB Eindhoven, The Netherlands#TAB#"],"affiliations":[{"raw_affiliation_string":"Technische Universiteit Eindhoven, Eindhoven, The Netherlands","institution_ids":["https://openalex.org/I83019370"]},{"raw_affiliation_string":"Technische Universiteit Eindhoven, Den Dolech 2, P.O. Box 513, 5600 MB Eindhoven, The Netherlands#TAB#","institution_ids":["https://openalex.org/I83019370"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027088423"],"corresponding_institution_ids":["https://openalex.org/I83019370"],"apc_list":null,"apc_paid":null,"fwci":18.3492,"has_fulltext":false,"cited_by_count":66,"citation_normalized_percentile":{"value":0.99016625,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"592","last_page":"595"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9990000128746033,"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":0.9990000128746033,"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":0.991599977016449,"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/T11719","display_name":"Data Quality and Management","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8256174325942993},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6754412651062012},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.6253029108047485},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.588212251663208},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.500199556350708},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.49580439925193787},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46845316886901855},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42935389280319214},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10014691948890686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256174325942993},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6754412651062012},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.6253029108047485},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.588212251663208},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.500199556350708},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.49580439925193787},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46845316886901855},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42935389280319214},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10014691948890686},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icsm.2012.6405329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsm.2012.6405329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 28th IEEE International Conference on Software Maintenance (ICSM)","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.tue.nl:openaire_cris_publications/ccfff2cb-5576-4e00-97b3-b7cbc9d5d414","is_oa":false,"landing_page_url":"https://research.tue.nl/en/publications/ccfff2cb-5576-4e00-97b3-b7cbc9d5d414","pdf_url":null,"source":{"id":"https://openalex.org/S4406922641","display_name":"TU/e Research Portal","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Kouters, E T M, Vasilescu, B N, Serebrenik, A & Brand, van den, M G J 2012, Who's who in Gnome : using LSA to merge software repository identities. in Proceedings of the Early Research Achievements (ERA) track of the 28th IEEE International Conference on Software Maintenance (ICSM 2012, Trento, Italy, September 23-30, 2012). Institute of Electrical and Electronics Engineers, Piscataway, pp. 592-595, conference; 28th IEEE International Conference on Software Maintenance; 2012-09-23; 2012-09-30, 23/09/12. https://doi.org/10.1109/ICSM.2012.6405329","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:736454","is_oa":false,"landing_page_url":"http://library.tue.nl/csp/dare/LinkToRepository.csp?recordnumber=736454","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.457.1427","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.457.1427","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.win.tue.nl/~bvasiles/papers/era12.pdf","raw_type":"text"},{"id":"pmh:oai:library.tue.nl:736454","is_oa":false,"landing_page_url":"http://repository.tue.nl/736454","pdf_url":null,"source":{"id":"https://openalex.org/S4406923046","display_name":"TU/e Research Portal (Eindhoven University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:tue:oai:pure.tue.nl:publications/ccfff2cb-5576-4e00-97b3-b7cbc9d5d414","is_oa":false,"landing_page_url":"https://research.tue.nl/nl/publications/ccfff2cb-5576-4e00-97b3-b7cbc9d5d414","pdf_url":null,"source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the Early Research Achievements (ERA) track of the 28th IEEE International Conference on Software Maintenance (ICSM 2012, Trento, Italy, September 23-30, 2012), 592 - 595","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","score":0.6000000238418579,"id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1983578042","https://openalex.org/W1990566545","https://openalex.org/W2039001182","https://openalex.org/W2039785095","https://openalex.org/W2076279155","https://openalex.org/W2079081534","https://openalex.org/W2119410041","https://openalex.org/W2136101509","https://openalex.org/W2163960678","https://openalex.org/W3150747159","https://openalex.org/W4240701274","https://openalex.org/W4251218026","https://openalex.org/W4252434862","https://openalex.org/W6648149850"],"related_works":["https://openalex.org/W83344948","https://openalex.org/W2350178533","https://openalex.org/W2001121861","https://openalex.org/W2350230178","https://openalex.org/W2351030537","https://openalex.org/W2101966962","https://openalex.org/W2119135658","https://openalex.org/W2364562957","https://openalex.org/W2802443881","https://openalex.org/W2354429408"],"abstract_inverted_index":{"Understanding":[0],"an":[1,5],"individual's":[2],"contribution":[3],"to":[4,15,39,61,111,131],"ecosystem":[6,20],"often":[7],"necessitates":[8],"integrating":[9],"information":[10],"from":[11],"multiple":[12],"repositories":[13,25],"corresponding":[14],"different":[16,22,36,49],"projects":[17],"within":[18],"the":[19,40,65,69,72,74,76,82,85,99],"or":[21],"kinds":[23],"of":[24,84,106,114,137,147,164],"(e.g.,":[26],"mail":[27],"archives":[28],"and":[29,103,141,166],"version":[30],"control":[31],"systems).":[32],"However,":[33],"recognising":[34],"that":[35,54],"contributions":[37],"belong":[38],"same":[41,70],"contributor":[42],"is":[43,52],"challenging,":[44],"since":[45],"developers":[46],"may":[47],"use":[48],"aliases.":[50],"It":[51],"known":[53],"existing":[55,107,160],"identity":[56,121],"merging":[57,122],"algorithms":[58,108,161],"are":[59],"sensitive":[60],"large":[62,89],"discrepancies":[63],"between":[64],"aliases":[66],"used":[67],"by":[68,145],"individual:":[71],"noisier":[73],"data,":[75],"worse":[77],"their":[78],"performance.":[79],"To":[80],"assess":[81],"scale":[83],"problem":[86],"for":[87],"a":[88,119,156],"software":[90],"ecosystem,":[91],"we":[92],"study":[93],"all":[94],"Gnome":[95,150],"Git":[96,151],"repositories,":[97],"classify":[98],"differences":[100,138],"in":[101,139,162],"aliases,":[102,140],"discuss":[104],"robustness":[105],"with":[109],"respect":[110],"these":[112],"types":[113,136],"differences.":[115],"We":[116],"then":[117],"propose":[118],"new":[120],"algorithm":[123],"based":[124],"on":[125,149,168],"Latent":[126],"Semantic":[127],"Analysis":[128],"(LSA),":[129],"designed":[130],"be":[132],"robust":[133],"against":[134],"more":[135],"evaluate":[142],"it":[143],"empirically":[144],"means":[146],"cross-validation":[148],"authors.":[152],"Our":[153],"results":[154],"show":[155],"clear":[157],"improvement":[158],"over":[159],"terms":[163],"precision":[165],"recall":[167],"worst-case":[169],"input":[170],"data.":[171]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":7}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}