{"id":"https://openalex.org/W3140103367","doi":"https://doi.org/10.1109/msr.2012.6224294","title":"GHTorrent: Github's data from a firehose","display_name":"GHTorrent: Github's data from a firehose","publication_year":2012,"publication_date":"2012-06-01","ids":{"openalex":"https://openalex.org/W3140103367","doi":"https://doi.org/10.1109/msr.2012.6224294","mag":"3140103367"},"language":"en","primary_location":{"id":"doi:10.1109/msr.2012.6224294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2012.6224294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th IEEE Working Conference on Mining Software Repositories (MSR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5043864604","display_name":"Georgios Gousios","orcid":"https://orcid.org/0000-0002-8495-7939"},"institutions":[{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Georgios Gousios","raw_affiliation_strings":["Department of Management Science and Technology, Athens University of Economics and Business, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Management Science and Technology, Athens University of Economics and Business, Athens, Greece","institution_ids":["https://openalex.org/I73142707"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021948425","display_name":"Diomidis Spinellis","orcid":"https://orcid.org/0000-0003-4231-1897"},"institutions":[{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"D. Spinellis","raw_affiliation_strings":["Department of Management Science and Technology, Athens University of Economics and Business, Athens, Greece"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Management Science and Technology, Athens University of Economics and Business, Athens, Greece","institution_ids":["https://openalex.org/I73142707"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I73142707"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":206,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9962000250816345,"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"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9926000237464905,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.834388256072998},{"id":"https://openalex.org/keywords/mirroring","display_name":"Mirroring","score":0.739835262298584},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6599192023277283},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5414886474609375},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5356743931770325},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4902186989784241},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4463905394077301},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3797067403793335},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.338126003742218},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16834014654159546}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.834388256072998},{"id":"https://openalex.org/C189645446","wikidata":"https://www.wikidata.org/wiki/Q350865","display_name":"Mirroring","level":2,"score":0.739835262298584},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6599192023277283},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5414886474609375},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5356743931770325},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4902186989784241},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4463905394077301},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3797067403793335},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.338126003742218},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16834014654159546},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","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},{"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/msr.2012.6224294","is_oa":false,"landing_page_url":"https://doi.org/10.1109/msr.2012.6224294","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 9th IEEE Working Conference on Mining Software Repositories (MSR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5600000023841858}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335322","display_name":"European Regional Development Fund","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W7070757","https://openalex.org/W641258496","https://openalex.org/W1577231857","https://openalex.org/W1819759706","https://openalex.org/W2025007121","https://openalex.org/W2042753694","https://openalex.org/W2076279155","https://openalex.org/W2080962405","https://openalex.org/W2110366513","https://openalex.org/W2111861834","https://openalex.org/W2115052242","https://openalex.org/W2119531903","https://openalex.org/W2136101509","https://openalex.org/W2167117640","https://openalex.org/W2173213060","https://openalex.org/W2302890201","https://openalex.org/W2621134924","https://openalex.org/W3144106047","https://openalex.org/W4240398231","https://openalex.org/W4240701274","https://openalex.org/W6677739895"],"related_works":["https://openalex.org/W2081134829","https://openalex.org/W2012196799","https://openalex.org/W2914953798","https://openalex.org/W2016936103","https://openalex.org/W1969752774","https://openalex.org/W2551163313","https://openalex.org/W2294049764","https://openalex.org/W2108584188","https://openalex.org/W1980969160","https://openalex.org/W2404041551"],"abstract_inverted_index":{"A":[0],"common":[1],"requirement":[2],"of":[3,14,72],"many":[4],"empirical":[5],"software":[6,17],"engineering":[7],"studies":[8],"is":[9],"the":[10,20,48,51,83,94,103],"acquisition":[11],"and":[12,33,54,76,79,97,100,109],"curation":[13],"data":[15],"from":[16],"repositories.":[18],"During":[19],"last":[21],"few":[22],"years,":[23],"GitHub":[24,36],"has":[25],"emerged":[26],"as":[27,86],"a":[28,67,87],"popular":[29],"project":[30,61],"hosting,":[31],"mirroring":[32],"collaboration":[34],"platform.":[35],"provides":[37],"an":[38],"extensive":[39],"REST":[40],"API,":[41],"which":[42],"enables":[43],"researchers":[44],"to":[45,50,65,82],"retrieve":[46],"both":[47],"commits":[49],"projects'":[52],"repositories":[53],"events":[55],"generated":[56],"through":[57],"user":[58],"actions":[59],"on":[60],"resources.":[62],"GHTorrent":[63],"aims":[64],"create":[66],"scalable":[68],"off":[69],"line":[70],"mirror":[71],"GitHub's":[73],"event":[74],"streams":[75],"persistent":[77],"data,":[78],"offer":[80],"it":[81],"research":[84],"community":[85],"service.":[88],"In":[89],"this":[90],"paper,":[91],"we":[92],"present":[93],"project's":[95],"design":[96],"initial":[98],"implementation":[99],"demonstrate":[101],"how":[102],"provided":[104],"datasets":[105],"can":[106],"be":[107],"queried":[108],"processed.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":25},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":27},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":31},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":7}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}