{"id":"https://openalex.org/W4414097079","doi":"https://doi.org/10.3390/info16090774","title":"A Generalized Method for Filtering Noise in Open-Source Project Selection","display_name":"A Generalized Method for Filtering Noise in Open-Source Project Selection","publication_year":2025,"publication_date":"2025-09-06","ids":{"openalex":"https://openalex.org/W4414097079","doi":"https://doi.org/10.3390/info16090774"},"language":"en","primary_location":{"id":"doi:10.3390/info16090774","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16090774","pdf_url":"https://www.mdpi.com/2078-2489/16/9/774/pdf?version=1757147071","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/16/9/774/pdf?version=1757147071","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030009218","display_name":"Yi Ding","orcid":"https://orcid.org/0000-0003-3406-9770"},"institutions":[{"id":"https://openalex.org/I4210100789","display_name":"Wuhan College","ror":"https://ror.org/01dashf18","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210100789"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Ding","raw_affiliation_strings":["Information College, Wuhan Vocational College of Software and Engineering, Wuhan 430205, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information College, Wuhan Vocational College of Software and Engineering, Wuhan 430205, China","institution_ids":["https://openalex.org/I4210100789"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101406652","display_name":"Qing Fang","orcid":"https://orcid.org/0000-0002-7286-5586"},"institutions":[{"id":"https://openalex.org/I4210116247","display_name":"Jingchu University of Technology","ror":"https://ror.org/037kvhq82","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210116247"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qing Fang","raw_affiliation_strings":["Normal College, Jingchu University of Technology, Jingmen 448000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Normal College, Jingchu University of Technology, Jingmen 448000, China","institution_ids":["https://openalex.org/I4210116247"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065215852","display_name":"Xiaoyan Liu","orcid":"https://orcid.org/0000-0002-1768-9014"},"institutions":[{"id":"https://openalex.org/I4210100789","display_name":"Wuhan College","ror":"https://ror.org/01dashf18","country_code":"CN","type":"nonprofit","lineage":["https://openalex.org/I4210100789"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyan Liu","raw_affiliation_strings":["Information College, Wuhan Vocational College of Software and Engineering, Wuhan 430205, China"],"raw_orcid":"https://orcid.org/0000-0002-1768-9014","affiliations":[{"raw_affiliation_string":"Information College, Wuhan Vocational College of Software and Engineering, Wuhan 430205, China","institution_ids":["https://openalex.org/I4210100789"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101406652"],"corresponding_institution_ids":["https://openalex.org/I4210116247"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33318367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"9","first_page":"774","last_page":"774"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9829000234603882,"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":0.9193000197410583,"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/generality","display_name":"Generality","score":0.6280999779701233},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5644000172615051},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5440000295639038},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5268999934196472},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.5044999718666077},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4794999957084656},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42739999294281006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6996999979019165},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.6280999779701233},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5644000172615051},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5519000291824341},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5440000295639038},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5353999733924866},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5268999934196472},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.5044999718666077},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4794999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.429500013589859},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42739999294281006},{"id":"https://openalex.org/C21569690","wikidata":"https://www.wikidata.org/wiki/Q94702","display_name":"Collaborative filtering","level":3,"score":0.38449999690055847},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C5481197","wikidata":"https://www.wikidata.org/wiki/Q16766476","display_name":"Decision tree learning","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/info16090774","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16090774","pdf_url":"https://www.mdpi.com/2078-2489/16/9/774/pdf?version=1757147071","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f2e69e814093499cbf1a6cba8e6b5335","is_oa":true,"landing_page_url":"https://doaj.org/article/f2e69e814093499cbf1a6cba8e6b5335","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 16, Iss 9, p 774 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/info16090774","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info16090774","pdf_url":"https://www.mdpi.com/2078-2489/16/9/774/pdf?version=1757147071","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414097079.pdf","grobid_xml":"https://content.openalex.org/works/W4414097079.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1015675232","https://openalex.org/W1914969610","https://openalex.org/W1968020518","https://openalex.org/W1972386298","https://openalex.org/W1974270771","https://openalex.org/W2050065895","https://openalex.org/W2056894403","https://openalex.org/W2122041620","https://openalex.org/W2288177242","https://openalex.org/W2347053969","https://openalex.org/W2398941234","https://openalex.org/W2559885217","https://openalex.org/W2599685535","https://openalex.org/W2601908482","https://openalex.org/W2755552262","https://openalex.org/W2773867142","https://openalex.org/W2794176882","https://openalex.org/W2884854827","https://openalex.org/W2910750801","https://openalex.org/W2921110186","https://openalex.org/W2940740603","https://openalex.org/W2946270456","https://openalex.org/W2953729744","https://openalex.org/W2963203256","https://openalex.org/W2963548617","https://openalex.org/W2971732167","https://openalex.org/W3006568433","https://openalex.org/W3013745307","https://openalex.org/W3014164501","https://openalex.org/W3103719551","https://openalex.org/W3140103367","https://openalex.org/W3147233559","https://openalex.org/W3215657252","https://openalex.org/W4224330577","https://openalex.org/W4251460506","https://openalex.org/W4387350467","https://openalex.org/W4401454927"],"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":{"GitHub":[0],"hosts":[1],"over":[2],"10":[3],"million":[4],"repositories,":[5],"providing":[6],"researchers":[7,150],"with":[8,57,130,159],"vast":[9],"opportunities":[10],"to":[11,84,136,151],"study":[12],"diverse":[13],"software":[14],"engineering":[15],"problems.":[16],"However,":[17],"as":[18],"anyone":[19],"can":[20],"create":[21],"a":[22],"repository":[23],"for":[24,47],"any":[25],"purpose":[26],"at":[27],"no":[28],"cost,":[29],"open-source":[30,45,154],"platforms":[31],"contain":[32],"many":[33],"non-cooperative":[34],"or":[35],"non-developmental":[36],"noise":[37,145],"projects":[38,46,52,59,155],"(e.g.,":[39,53],"repositories":[40],"of":[41],"dotfiles).":[42],"When":[43],"selecting":[44,147],"analysis,":[48],"mixing":[49],"collaborative":[50],"coding":[51],"machine":[54],"learning":[55],"frameworks)":[56],"noisy":[58],"may":[60],"bias":[61],"research":[62],"findings.":[63],"To":[64],"solve":[65],"this":[66],"problem,":[67],"we":[68],"optimize":[69],"the":[70,95],"Semi-Automatic":[71],"Decision":[72],"Tree":[73],"Method":[74],"(SADTM),":[75],"an":[76,131],"existing":[77,117,141],"Collaborative":[78],"Coding":[79],"Project":[80],"(CCP)":[81],"classification":[82,106],"method,":[83],"improve":[85],"its":[86],"generality":[87],"and":[88,99,146],"accuracy.":[89,161],"We":[90],"evaluate":[91],"our":[92],"method":[93,139],"on":[94],"GHTorrent":[96],"dataset":[97],"(2012\u20132020)":[98],"find":[100],"that":[101],"it":[102,112,126],"effectively":[103],"enhances":[104],"CCP":[105],"in":[107,143],"two":[108],"key":[109],"ways:":[110],"(1)":[111],"demonstrates":[113],"greater":[114],"stability":[115],"than":[116],"methods,":[118],"yielding":[119],"consistent":[120],"results":[121],"across":[122],"different":[123],"datasets;":[124],"(2)":[125],"achieves":[127],"high":[128],"precision,":[129],"F-measure":[132],"ranging":[133],"from":[134,156],"0.780":[135],"0.893.":[137],"Our":[138],"outperforms":[140],"techniques":[142],"filtering":[144],"CCPs,":[148],"enabling":[149],"extract":[152],"high-quality":[153],"candidate":[157],"samples":[158],"reliable":[160]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}