{"id":"https://openalex.org/W4386072357","doi":"https://doi.org/10.1109/smartnets58706.2023.10215598","title":"Extracting Insights from Big Source Code Repositories with Automatic Clustering of Projects by File Names and Types","display_name":"Extracting Insights from Big Source Code Repositories with Automatic Clustering of Projects by File Names and Types","publication_year":2023,"publication_date":"2023-07-25","ids":{"openalex":"https://openalex.org/W4386072357","doi":"https://doi.org/10.1109/smartnets58706.2023.10215598"},"language":"en","primary_location":{"id":"doi:10.1109/smartnets58706.2023.10215598","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smartnets58706.2023.10215598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","raw_type":"proceedings-article"},"type":"article","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/A5092675706","display_name":"Yury Yakhno","orcid":null},"institutions":[{"id":"https://openalex.org/I4210152669","display_name":"Teknoloji Arastirma ve Gelistirme Endustriyel Urunler Bilisim Teknolojileri San Tic","ror":"https://ror.org/040nc8096","country_code":"TR","type":"company","lineage":["https://openalex.org/I4210152669"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Yury Yakhno","raw_affiliation_strings":["NetRD Information Technologies and Telecommunication,Istanbul,Turkey","NetRD Information Technologies and Telecommunication, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"NetRD Information Technologies and Telecommunication,Istanbul,Turkey","institution_ids":["https://openalex.org/I4210152669"]},{"raw_affiliation_string":"NetRD Information Technologies and Telecommunication, Istanbul, Turkey","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047113099","display_name":"Selin Metin","orcid":"https://orcid.org/0000-0002-2231-388X"},"institutions":[{"id":"https://openalex.org/I4210152669","display_name":"Teknoloji Arastirma ve Gelistirme Endustriyel Urunler Bilisim Teknolojileri San Tic","ror":"https://ror.org/040nc8096","country_code":"TR","type":"company","lineage":["https://openalex.org/I4210152669"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Selin Metin","raw_affiliation_strings":["NetRD Information Technologies and Telecommunication,Istanbul,Turkey","NetRD Information Technologies and Telecommunication, Istanbul, Turkey"],"affiliations":[{"raw_affiliation_string":"NetRD Information Technologies and Telecommunication,Istanbul,Turkey","institution_ids":["https://openalex.org/I4210152669"]},{"raw_affiliation_string":"NetRD Information Technologies and Telecommunication, Istanbul, Turkey","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5092675706"],"corresponding_institution_ids":["https://openalex.org/I4210152669"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17439623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9997000098228455,"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":0.9997000098228455,"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":0.994700014591217,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9894000291824341,"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/computer-science","display_name":"Computer science","score":0.7868103384971619},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.46564874053001404},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.46536707878112793},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4450306296348572},{"id":"https://openalex.org/keywords/kpi-driven-code-analysis","display_name":"KPI-driven code analysis","score":0.4133055508136749},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3955034911632538},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38615429401397705},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38491034507751465},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.34202128648757935},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3253028392791748},{"id":"https://openalex.org/keywords/static-program-analysis","display_name":"Static program analysis","score":0.32188743352890015},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18277239799499512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7868103384971619},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.46564874053001404},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.46536707878112793},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4450306296348572},{"id":"https://openalex.org/C121957198","wikidata":"https://www.wikidata.org/wiki/Q14365593","display_name":"KPI-driven code analysis","level":5,"score":0.4133055508136749},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3955034911632538},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38615429401397705},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38491034507751465},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.34202128648757935},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3253028392791748},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.32188743352890015},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18277239799499512}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smartnets58706.2023.10215598","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/smartnets58706.2023.10215598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 International Conference on Smart Applications, Communications and Networking (SmartNets)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2187358498","https://openalex.org/W2188947835","https://openalex.org/W2267596186","https://openalex.org/W2753453462","https://openalex.org/W2795059349","https://openalex.org/W2990498699","https://openalex.org/W3020436075","https://openalex.org/W3094829982","https://openalex.org/W4210314036","https://openalex.org/W4294170691","https://openalex.org/W4297819591","https://openalex.org/W6682691769","https://openalex.org/W6687702573","https://openalex.org/W6693361605","https://openalex.org/W6803068904"],"related_works":["https://openalex.org/W377327559","https://openalex.org/W4210653322","https://openalex.org/W1976804602","https://openalex.org/W2316077753","https://openalex.org/W3006945192","https://openalex.org/W2149598945","https://openalex.org/W4206152185","https://openalex.org/W2390085541","https://openalex.org/W1990888989","https://openalex.org/W2139694402"],"abstract_inverted_index":{"Software":[0,40],"project":[1,46,117,133,156],"delivery":[2,91],"requires":[3],"a":[4,18,137],"set":[5,142],"of":[6,14,20,143,152,165,176,185],"related":[7,95],"activities":[8,16,48],"to":[9,44,104,113,116,122,162],"be":[10,51,87],"conducted.":[11],"The":[12,97],"output":[13],"these":[15],"form":[17],"collection":[19,77],"unstructured":[21],"data":[22,76],"such":[23],"as":[24,119],"specifications,":[25],"requirements,":[26],"manuals,":[27],"source":[28],"code":[29,58,63,170],"and":[30,49,74,109,150,172,183],"packaging":[31],"files":[32,154],"which":[33,84,145],"is":[34,134,146],"stored":[35],"in":[36,168],"configuration":[37],"management":[38,47],"systems.":[39],"repositories":[41,108,171],"are":[42,160],"infrastructures":[43],"support":[45],"can":[50,86],"composed":[52],"with":[53],"several":[54],"systems":[55],"that":[56],"include":[57],"change":[59],"management,":[60],"bug":[61],"tracking,":[62],"review,":[64],"build":[65],"system,":[66],"release":[67],"binaries,":[68],"wikis,":[69],"forums,":[70],"etc.":[71],"This":[72],"large":[73,106],"variable":[75],"provides":[78],"opportunities":[79],"for":[80,89],"text":[81],"mining":[82],"tasks":[83],"further":[85],"utilized":[88],"software":[90,107,132],"or":[92,141],"business":[93,125],"intelligence":[94],"goals.":[96],"proposed":[98],"approach":[99],"uses":[100],"machine":[101],"learning":[102],"methods":[103],"inspect":[105],"classifies":[110],"the":[111,128,153,177,186],"results":[112],"propose":[114],"insights":[115],"managers":[118],"an":[120],"aide":[121],"make":[123],"strategic":[124],"decisions.":[126],"In":[127],"present":[129],"work":[130],"every":[131],"described":[135],"by":[136],"certain":[138],"representation":[139],"(vector":[140],"vectors),":[144],"constructed":[147],"from":[148,155],"names":[149,182],"types":[151,184],"content.":[157],"These":[158],"representations":[159],"used":[161,181],"find":[163],"clusters":[164],"similar":[166],"projects":[167],"big":[169],"highlight":[173],"specific":[174],"properties":[175],"found":[178],"groups:":[179],"most":[180],"file.":[187]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}
