{"id":"https://openalex.org/W4308643129","doi":"https://doi.org/10.1145/3540250.3569448","title":"Performing large-scale mining studies: from start to finish (tutorial)","display_name":"Performing large-scale mining studies: from start to finish (tutorial)","publication_year":2022,"publication_date":"2022-11-07","ids":{"openalex":"https://openalex.org/W4308643129","doi":"https://doi.org/10.1145/3540250.3569448"},"language":"en","primary_location":{"id":"doi:10.1145/3540250.3569448","doi":"https://doi.org/10.1145/3540250.3569448","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3540250.3569448","pdf_url":null,"source":{"id":"https://openalex.org/S4363608883","display_name":"ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE)","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 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"},"volume":null,"type":"conference-abstract","is_traditional":false,"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/A5057293289","display_name":"Robert Dyer","orcid":"https://orcid.org/0000-0001-9571-5567","observed_orcids":["https://orcid.org/0000-0001-9571-5567"]},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robert Dyer","raw_affiliation_strings":["University of Nebraska-Lincoln, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nebraska-Lincoln, USA","institution_ids":["https://openalex.org/I114395901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014047598","display_name":"Samuel W. Flint","orcid":"https://orcid.org/0000-0002-8023-9710","observed_orcids":["https://orcid.org/0000-0002-8023-9710"]},"institutions":[{"id":"https://openalex.org/I114395901","display_name":"University of Nebraska\u2013Lincoln","ror":"https://ror.org/043mer456","country_code":"US","type":"education","lineage":["https://openalex.org/I114395901"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samuel W. Flint","raw_affiliation_strings":["University of Nebraska-Lincoln, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Nebraska-Lincoln, USA","institution_ids":["https://openalex.org/I114395901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114395901"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1822","last_page":"1822"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9955999851226807,"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":0.9955999851226807,"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":0.0024999999441206455,"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":0.0010000000474974513,"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/software-mining","display_name":"software mining","score":0.6970000267028809},{"id":"https://openalex.org/keywords/open-source-software-repositories","display_name":"open-source repositories","score":0.8849999904632568},{"id":"https://openalex.org/keywords/boa","display_name":"Boas","score":0.7570000290870667},{"id":"https://openalex.org/keywords/replication-packages","display_name":"replication packages","score":0.8240000009536743},{"id":"https://openalex.org/keywords/open-science","display_name":"open science","score":0.9559999704360962},{"id":"https://openalex.org/keywords/vs-code-extension","display_name":"VS Code extension","score":0.6610000133514404},{"id":"https://openalex.org/keywords/zenodo","display_name":"Zenodo","score":0.753000020980835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8256129622459412},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7865478992462158},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.6124860048294067},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6073941588401794},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5526795387268066},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.547261118888855},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.5464798212051392},{"id":"https://openalex.org/C150292731","wikidata":"https://www.wikidata.org/wiki/Q1342704","display_name":"Code review","level":5,"score":0.5335204005241394},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4751448631286621},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4247209429740906},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.41623854637145996},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33785179257392883},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3301617205142975},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.3289252817630768},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.239761620759964},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16999360918998718},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15019160509109497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09778746962547302},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3540250.3569448","doi":"https://doi.org/10.1145/3540250.3569448","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3540250.3569448","pdf_url":null,"source":{"id":"https://openalex.org/S4363608883","display_name":"ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE)","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 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W17540253","https://openalex.org/W4232691406","https://openalex.org/W7036335984","https://openalex.org/W2158110904","https://openalex.org/W1826771676","https://openalex.org/W4398239251","https://openalex.org/W2020834211","https://openalex.org/W4393593969","https://openalex.org/W2997821164","https://openalex.org/W2024585111"],"abstract_inverted_index":{"Modern":[0],"software":[1,9,27,98],"engineering":[2],"research":[3,17],"often":[4],"relies":[5],"on":[6,71,143],"mining":[7,97],"open-source":[8,54],"repositories,":[10],"to":[11,39,91,108,121],"either":[12],"provide":[13],"motivation":[14],"for":[15,83,96],"their":[16],"problems":[18],"and/or":[19],"evaluation":[20],"of":[21,53,62],"the":[22,93,129],"proposed":[23],"approach.":[24],"Mining":[25],"ultra-large-scale":[26],"repositories":[28],"is":[29,141],"still":[30],"a":[31,63,136],"difficult":[32],"task,":[33],"requiring":[34],"substantial":[35],"expertise":[36],"and":[37,111,115,133],"access":[38],"significant":[40],"hardware.":[41],"Tools":[42],"such":[43,77],"as":[44],"Boa":[45,94,113,132],"can":[46,125],"help":[47,109],"researchers":[48,124],"easily":[49,127],"mine":[50],"large":[51],"numbers":[52],"repositories.":[55],"There":[56],"has":[57],"also":[58,116],"recently":[59],"been":[60],"more":[61,126],"push":[64],"toward":[65],"open":[66],"science,":[67],"with":[68],"an":[69],"emphasis":[70],"making":[72],"replication":[73,78,138],"packages":[74,79],"available.":[75],"Building":[76],"incurs":[80],"additional":[81],"workload":[82],"researchers.":[84],"In":[85],"this":[86],"tutorial,":[87],"we":[88],"teach":[89],"how":[90,123],"use":[92],"infrastructure":[95],"repository":[99],"data.":[100],"We":[101],"leverage":[102,117],"Boa\u2019s":[103,118],"VS":[104],"Code":[105],"IDE":[106],"extension":[107],"write":[110],"submit":[112],"queries,":[114],"study":[119],"template":[120],"show":[122],"analyze":[128],"output":[130],"from":[131],"automatically":[134],"produce":[135],"suitable":[137],"package":[139],"that":[140],"published":[142],"Zenodo.":[144]},"counts_by_year":[],"updated_date":"2026-10-05T09:50:58.205359","created_date":"2022-11-13T00:00:00"}
