{"id":"https://openalex.org/W4409629732","doi":"https://doi.org/10.5220/0013289000003928","title":"Detecting Duplicate Effort in GitHub Contributions","display_name":"Detecting Duplicate Effort in GitHub Contributions","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409629732","doi":"https://doi.org/10.5220/0013289000003928"},"language":"en","primary_location":{"id":"doi:10.5220/0013289000003928","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0013289000003928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pureadmin.qub.ac.uk/ws/files/625342932/ENASE2025.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117231160","display_name":"James Galbraith","orcid":null},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Galbraith","raw_affiliation_strings":["School of Electronics, Electrical Engineering and Computer Science, Queen\u2019s University Belfast, Belfast, BT71NN, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen\u2019s University Belfast, Belfast, BT71NN, U.K","institution_ids":["https://openalex.org/I126231945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005179962","display_name":"Des Greer","orcid":"https://orcid.org/0000-0001-6367-9274"},"institutions":[{"id":"https://openalex.org/I126231945","display_name":"Queen's University Belfast","ror":"https://ror.org/00hswnk62","country_code":"GB","type":"education","lineage":["https://openalex.org/I126231945"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Des Greer","raw_affiliation_strings":["School of Electronics, Electrical Engineering and Computer Science, Queen\u2019s University Belfast, Belfast, BT71NN, U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics, Electrical Engineering and Computer Science, Queen\u2019s University Belfast, Belfast, BT71NN, U.K","institution_ids":["https://openalex.org/I126231945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126231945"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"520","last_page":"529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9945999979972839,"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":0.9945999979972839,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.978600025177002,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.7495631575584412}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7495631575584412}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0013289000003928","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0013289000003928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/649c5ac5-5a45-4a8e-b4c9-046278d21a47","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/649c5ac5-5a45-4a8e-b4c9-046278d21a47","pdf_url":"https://pureadmin.qub.ac.uk/ws/files/625342932/ENASE2025.pdf","source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Galbraith, J & Greer, D 2025, Detecting duplicate effort in GitHub contributions. in M Mannion , T Mannisto & L Maciaszek (eds), Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering, ENASE 2025. vol. 1, Proceedings of the International Conference on Evaluation of Novel Approaches to Software, SciTePress, pp. 520-529, 20th International Conference on Evaluation of Novel Approaches to Software Engineering 2025, Porto, Portugal, 04/04/2025. https://doi.org/10.5220/0013289000003928","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:pure.qub.ac.uk/portal:publications/649c5ac5-5a45-4a8e-b4c9-046278d21a47","is_oa":true,"landing_page_url":"https://pure.qub.ac.uk/en/publications/649c5ac5-5a45-4a8e-b4c9-046278d21a47","pdf_url":"https://pureadmin.qub.ac.uk/ws/files/625342932/ENASE2025.pdf","source":{"id":"https://openalex.org/S4306402319","display_name":"Research Portal (Queen's University Belfast)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126231945","host_organization_name":"Queen's University Belfast","host_organization_lineage":["https://openalex.org/I126231945"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Galbraith, J & Greer, D 2025, Detecting duplicate effort in GitHub contributions. in M Mannion , T Mannisto & L Maciaszek (eds), Proceedings of the 20th International Conference on Evaluation of Novel Approaches to Software Engineering, ENASE 2025. vol. 1, Proceedings of the International Conference on Evaluation of Novel Approaches to Software, SciTePress, pp. 520-529, 20th International Conference on Evaluation of Novel Approaches to Software Engineering 2025, Porto, Portugal, 04/04/2025. https://doi.org/10.5220/0013289000003928","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4409629732.pdf","grobid_xml":"https://content.openalex.org/works/W4409629732.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","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"],"abstract_inverted_index":{"The":[0,63],"pull-based":[1],"development":[2],"model":[3,103,124],"allows":[4],"collaborators":[5],"to":[6,11,57,90,106],"develop":[7],"and":[8,22,69,85,113,117,136,159,175,184],"propose":[9],"changes":[10,30],"a":[12,55,163,169],"codebase.":[13],"However,":[14],"pull":[15,44,50,61,86,118,160,185],"requests":[16,51,87,161,186],"can":[17,27,128,152],"often":[18],"offer":[19],"duplicate":[20,24,43,60],"functionality":[21],"therefore":[23],"effort.":[25],"Users":[26],"also":[28],"request":[29],"via":[31],"issues,":[32],"the":[33,75,111,147,177],"text":[34],"of":[35,77,115,122,134,139,149],"which":[36],"could":[37],"provide":[38],"clues,":[39],"useful":[40],"in":[41,88,179],"determining":[42],"requests.":[45,62,119],"This":[46],"research":[47],"investigates":[48],"combining":[49,157],"with":[52,54,131],"issues":[53,84,116,158,183],"view":[56],"better":[58],"detecting":[59,180],"paper":[64],"reviews":[65],"existing":[66],"related":[67],"work":[68],"then":[70],"extends":[71],"this":[72,123],"by":[73,109,156],"investigating":[74],"use":[76],"natural":[78],"language":[79],"processing":[80],"(NLP)":[81],"on":[82,172],"combined":[83],"order":[89],"detect":[91],"duplicates.":[92],"Using":[93],"data":[94],"taken":[95],"from":[96,182],"15":[97],"popular":[98],"GitHub":[99],"repositories,":[100],"an":[101,132,142],"NLP":[102],"was":[104],"trained":[105],"predict":[107],"duplicates":[108,127,150,181],"comparing":[110],"title":[112],"description":[114],"An":[120],"evaluation":[121],"shows":[125,145],"that":[126,146],"be":[129,153],"detected":[130,151],"accuracy":[133],"93.9%":[135],"recall":[137],"rate":[138],"90.5%,":[140],"while":[141],"exploratory":[143],"study":[144],"volume":[148],"increased":[154],"dramatically":[155],"into":[162],"single":[164],"dataset.":[165],"These":[166],"results":[167],"show":[168],"significant":[170],"improvement":[171],"previous":[173],"studies":[174],"demonstrate":[176],"value":[178],"combined.<br/>":[187]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}