{"id":"https://openalex.org/W1992218759","doi":"https://doi.org/10.1145/1858996.1859088","title":"A sentence-matching method for automatic license identification of source code files","display_name":"A sentence-matching method for automatic license identification of source code files","publication_year":2010,"publication_date":"2010-09-20","ids":{"openalex":"https://openalex.org/W1992218759","doi":"https://doi.org/10.1145/1858996.1859088","mag":"1992218759"},"language":"en","primary_location":{"id":"doi:10.1145/1858996.1859088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1858996.1859088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM international conference on Automated software engineering","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/A5027592388","display_name":"Daniel M. Germ\u00e1n","orcid":"https://orcid.org/0000-0001-5661-4392"},"institutions":[{"id":"https://openalex.org/I212119943","display_name":"University of Victoria","ror":"https://ror.org/04s5mat29","country_code":"CA","type":"education","lineage":["https://openalex.org/I212119943"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Daniel M. German","raw_affiliation_strings":["University of Victoria, Victoria, BC, Canada","University of Victoria , Victoria , BC, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Victoria, Victoria, BC, Canada","institution_ids":["https://openalex.org/I212119943"]},{"raw_affiliation_string":"University of Victoria , Victoria , BC, Canada#TAB#","institution_ids":["https://openalex.org/I212119943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032853095","display_name":"Yuki Manabe","orcid":"https://orcid.org/0000-0002-5663-0074"},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yuki Manabe","raw_affiliation_strings":["Osaka University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102258593","display_name":"Katsuro Inoue","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Katsuro Inoue","raw_affiliation_strings":["Osaka University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University, Osaka, Japan","institution_ids":["https://openalex.org/I98285908"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":12.8453,"has_fulltext":false,"cited_by_count":98,"citation_normalized_percentile":{"value":0.98387877,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"437","last_page":"446"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9975000023841858,"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/T11675","display_name":"Open Source Software Innovations","score":0.9933000206947327,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8387819528579712},{"id":"https://openalex.org/keywords/license","display_name":"License","score":0.82499098777771},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.781793475151062},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.7097194194793701},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.674544095993042},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6148331165313721},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6041004061698914},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.563696026802063},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5585176944732666},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5145387053489685},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5009579658508301},{"id":"https://openalex.org/keywords/open-source","display_name":"Open source","score":0.4713130593299866},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3653399348258972},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36085695028305054},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2541459798812866},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25023943185806274},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1283860206604004},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08882567286491394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8387819528579712},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.82499098777771},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.781793475151062},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.7097194194793701},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.674544095993042},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6148331165313721},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6041004061698914},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.563696026802063},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5585176944732666},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5145387053489685},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5009579658508301},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.4713130593299866},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3653399348258972},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36085695028305054},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2541459798812866},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25023943185806274},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1283860206604004},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08882567286491394},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1858996.1859088","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1858996.1859088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/ACM international conference on Automated software engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.174.457","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.174.457","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://iip-lab.ics.es.osaka-u.ac.jp/%7Elab-db/betuzuri/archive/809/809.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1548392951","https://openalex.org/W1972653749","https://openalex.org/W1978301647","https://openalex.org/W1995709637","https://openalex.org/W2027370816","https://openalex.org/W2030470432","https://openalex.org/W2043726546","https://openalex.org/W2060942111","https://openalex.org/W2063401415","https://openalex.org/W2066154464","https://openalex.org/W2096282892","https://openalex.org/W2098230348","https://openalex.org/W2107838985","https://openalex.org/W2122662313","https://openalex.org/W2131265794","https://openalex.org/W2147209048","https://openalex.org/W2152759400","https://openalex.org/W2162517626","https://openalex.org/W2164914897","https://openalex.org/W2171606859"],"related_works":["https://openalex.org/W2036021480","https://openalex.org/W2546377002","https://openalex.org/W4285209474","https://openalex.org/W2046541848","https://openalex.org/W22571951","https://openalex.org/W4309247532","https://openalex.org/W3081674575","https://openalex.org/W4287673983","https://openalex.org/W2113128227","https://openalex.org/W3123068371"],"abstract_inverted_index":{"The":[0,38],"reuse":[1],"of":[2,15,40,49,61,86,106,125],"free":[3],"and":[4,72,111],"open":[5],"source":[6,51,67,122],"software":[7],"(FOSS)":[8],"components":[9],"is":[10,24,32,44,69],"becoming":[11],"more":[12],"prevalent.":[13],"One":[14],"the":[16,21,47,59,63,84,132],"major":[17],"challenges":[18,60],"in":[19,109,134],"finding":[20,25],"right":[22],"component":[23,43],"one":[26],"that":[27,31,99,101,127],"has":[28],"a":[29,41,74,91],"license":[30,39,64,107],"e":[33],"for":[34],"its":[35,50],"intended":[36],"use.":[37],"FOSS":[42,140],"determined":[45],"by":[46,89,139],"licenses":[48,136],"code":[52,68,123],"files.":[53],"In":[54],"this":[55],"paper,":[56],"we":[57],"describe":[58],"identifying":[62],"under":[65],"which":[66,135],"made":[70],"available,":[71],"propose":[73],"sentence-based":[75],"matching":[76],"algorithm":[77],"to":[78],"automatically":[79],"do":[80],"it.":[81],"We":[82,95,113],"demonstrate":[83],"feasibility":[85],"our":[87],"approach":[88],"implementing":[90],"tool":[92],"named":[93],"Ninka.":[94],"performed":[96,115],"an":[97,116],"evaluation":[98],"shows":[100],"Ninka":[102],"outperforms":[103],"other":[104],"methods":[105],"identification":[108],"precision":[110],"speed.":[112],"also":[114],"empirical":[117],"study":[118],"on":[119],"0.8":[120],"million":[121],"files":[124],"Debian":[126],"highlight":[128],"interesting":[129],"facts":[130],"about":[131],"manner":[133],"are":[137],"used":[138]},"counts_by_year":[{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
