{"id":"https://openalex.org/W2140952846","doi":"https://doi.org/10.1145/2597073.2597074","title":"The promises and perils of mining GitHub","display_name":"The promises and perils of mining GitHub","publication_year":2014,"publication_date":"2014-05-20","ids":{"openalex":"https://openalex.org/W2140952846","doi":"https://doi.org/10.1145/2597073.2597074","mag":"2140952846"},"language":"en","primary_location":{"id":"doi:10.1145/2597073.2597074","doi":"https://doi.org/10.1145/2597073.2597074","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597073.2597074","pdf_url":null,"source":{"id":"https://openalex.org/S7407088599","display_name":"International Conference on Mining Software Repositories (MSR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Working Conference on Mining Software Repositories","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5039702621","display_name":"Eirini Kalliamvakou","orcid":"https://orcid.org/0000-0002-7602-4581","observed_orcids":["https://orcid.org/0000-0002-7602-4581"]},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Eirini Kalliamvakou","raw_affiliation_strings":["University of Victoria, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043864604","display_name":"Georgios Gousios","orcid":"https://orcid.org/0000-0002-8495-7939","observed_orcids":["https://orcid.org/0000-0002-8495-7939"]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Georgios Gousios","raw_affiliation_strings":["Delft University of Technology, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039326697","display_name":"Kelly Blincoe","orcid":"https://orcid.org/0000-0003-4092-9706","observed_orcids":["https://orcid.org/0000-0003-4092-9706"]},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kelly Blincoe","raw_affiliation_strings":["University of Victoria, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054352353","display_name":"Leif Singer","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Leif Singer","raw_affiliation_strings":["University of Victoria, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027592388","display_name":"Daniel M. Germ\u00e1n","orcid":"https://orcid.org/0000-0001-5661-4392","observed_orcids":["https://orcid.org/0000-0001-5661-4392"]},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Daniel M. German","raw_affiliation_strings":["University of Victoria, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007049054","display_name":"Daniela Damian","orcid":"https://orcid.org/0000-0003-0826-5460","observed_orcids":["https://orcid.org/0000-0003-0826-5460"]},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Daniela Damian","raw_affiliation_strings":["University of Victoria, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, Canada","institution_ids":["https://openalex.org/I212119943"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":36.725,"has_fulltext":false,"cited_by_count":893,"citation_normalized_percentile":{"value":0.99967226,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"92","last_page":"101"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9452999830245972,"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":0.9452999830245972,"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/T11675","display_name":"Open Source Software Innovations","score":0.04450000077486038,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.00930000003427267,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/github","display_name":"GitHub","score":0.9769999980926514},{"id":"https://openalex.org/keywords/source-code-repositories","display_name":"software repositories","score":0.5849999785423279},{"id":"https://openalex.org/keywords/data-mining","display_name":"data mining","score":0.5799999833106995},{"id":"https://openalex.org/keywords/event-logs","display_name":"event logs","score":0.6840000152587891},{"id":"https://openalex.org/keywords/pull-requests","display_name":"pull requests","score":0.7250000238418579},{"id":"https://openalex.org/keywords/issues","display_name":"issues","score":0.5770000219345093},{"id":"https://openalex.org/keywords/commit","display_name":"commits","score":0.9610000252723694},{"id":"https://openalex.org/keywords/software-development","display_name":"software development","score":0.3840000033378601},{"id":"https://openalex.org/keywords/data-quality","display_name":"data quality","score":0.7699999809265137},{"id":"https://openalex.org/keywords/open-source-collaboration","display_name":"open source collaboration","score":0.4050000011920929}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8338068723678589},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.590968906879425},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5835482478141785},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.49005138874053955},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4753803312778473},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46421435475349426},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4243243932723999},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2597073.2597074","doi":"https://doi.org/10.1145/2597073.2597074","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2597073.2597074","pdf_url":null,"source":{"id":"https://openalex.org/S7407088599","display_name":"International Conference on Mining Software Repositories (MSR)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th Working Conference on Mining Software Repositories","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.728.3689","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.728.3689","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://thesegalgroup.org/wp-content/uploads/2014/04/githubChallenges.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W129985461","https://openalex.org/W1576624296","https://openalex.org/W1604074247","https://openalex.org/W1963578450","https://openalex.org/W1994360381","https://openalex.org/W1994922758","https://openalex.org/W2025674334","https://openalex.org/W2032342931","https://openalex.org/W2054905779","https://openalex.org/W2091990486","https://openalex.org/W2097886687","https://openalex.org/W2100196534","https://openalex.org/W2103188316","https://openalex.org/W2107294940","https://openalex.org/W2108050908","https://openalex.org/W2110385988","https://openalex.org/W2112357885","https://openalex.org/W2118174895","https://openalex.org/W2122702470","https://openalex.org/W2124100711","https://openalex.org/W2125854594","https://openalex.org/W2125889680","https://openalex.org/W2126166995","https://openalex.org/W2129164226","https://openalex.org/W2133561941","https://openalex.org/W2139092060","https://openalex.org/W2141558501","https://openalex.org/W2147122181","https://openalex.org/W2148854374","https://openalex.org/W2149231960","https://openalex.org/W2149783794","https://openalex.org/W2151553346","https://openalex.org/W2152094063","https://openalex.org/W2162520939","https://openalex.org/W2163592454","https://openalex.org/W2175631294","https://openalex.org/W3144106047","https://openalex.org/W4243240013"],"related_works":["https://openalex.org/W1914969610","https://openalex.org/W7096626958","https://openalex.org/W7098637162","https://openalex.org/W2620921533","https://openalex.org/W3162458071","https://openalex.org/W2404313524","https://openalex.org/W2073429012","https://openalex.org/W6931390008","https://openalex.org/W3140103367","https://openalex.org/W7159601717"],"abstract_inverted_index":{"With":[0],"over":[1],"10":[2],"million":[3],"git":[4],"repositories,":[5],"GitHub":[6,82,102,113,139],"is":[7,103,140],"becoming":[8],"one":[9],"of":[10,15,59,69,78,88,107,131,157,174],"the":[11,19,26,40,55,60,67,76,79,129,132,184],"most":[12],"important":[13],"source":[14,106],"software":[16,110,177],"artifacts":[17],"on":[18,44,109,180],"Internet.":[20],"Researchers":[21],"are":[22,134],"starting":[23],"to":[24,34,42,182],"mine":[25],"information":[27],"stored":[28],"in":[29,81,186],"GitHub's":[30,89],"event":[31],"logs,":[32],"trying":[33],"understand":[35],"how":[36,84,181],"its":[37],"users":[38,85],"employ":[39],"site":[41],"collaborate":[43],"software.":[45],"However,":[46],"so":[47],"far":[48],"there":[49],"have":[50],"been":[51],"no":[52],"studies":[53],"describing":[54],"quality":[56],"and":[57,83,95,136,147,153],"properties":[58],"data":[61,108,185],"available":[62],"from":[63],"GitHub.":[64,187],"We":[65,124,170],"document":[66],"results":[68,98],"an":[70],"empirical":[71],"study":[72],"aimed":[73],"at":[74],"understanding":[75],"characteristics":[77],"repositories":[80],"take":[86,118],"advantage":[87],"main":[90],"features---namely":[91],"commits,":[92],"pull":[93,159],"requests,":[94],"issues.":[96],"Our":[97],"indicate":[99],"that,":[100],"while":[101],"a":[104,149,172],"rich":[105],"development,":[111],"mining":[112],"for":[114,126,144,176],"research":[115],"purposes":[116],"should":[117],"various":[119],"potential":[120],"perils":[121],"into":[122],"consideration.":[123],"show,":[125],"example,":[127],"that":[128,138,154],"majority":[130],"projects":[133],"personal":[135],"inactive;":[137],"also":[141],"being":[142],"used":[143],"free":[145],"storage":[146],"as":[148,164],"Web":[150],"hosting":[151],"service;":[152],"almost":[155],"40%":[156],"all":[158],"requests":[160],"do":[161],"not":[162],"appear":[163],"merged,":[165],"even":[166],"though":[167],"they":[168],"were.":[169],"provide":[171],"set":[173],"recommendations":[175],"engineering":[178],"researchers":[179],"approach":[183]},"counts_by_year":[{"year":2026,"cited_by_count":114},{"year":2025,"cited_by_count":70},{"year":2024,"cited_by_count":62},{"year":2023,"cited_by_count":75},{"year":2022,"cited_by_count":68},{"year":2021,"cited_by_count":85},{"year":2020,"cited_by_count":81},{"year":2019,"cited_by_count":94},{"year":2018,"cited_by_count":71},{"year":2017,"cited_by_count":53},{"year":2016,"cited_by_count":49},{"year":2015,"cited_by_count":44},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2016-06-24T00:00:00"}