{"id":"https://openalex.org/W2142098106","doi":"https://doi.org/10.1587/transinf.2014edp7007","title":"Hierarchical Categorization of Open Source Software by Online Profiles","display_name":"Hierarchical Categorization of Open Source Software by Online Profiles","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W2142098106","doi":"https://doi.org/10.1587/transinf.2014edp7007","mag":"2142098106"},"language":"en","primary_location":{"id":"doi:10.1587/transinf.2014edp7007","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7007","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/9/E97.D_2014EDP7007/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/9/E97.D_2014EDP7007/_pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100453601","display_name":"Tao Wang","orcid":"https://orcid.org/0000-0002-8406-8672"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tao WANG","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology","Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101522100","display_name":"Huaimin Wang","orcid":"https://orcid.org/0000-0002-3245-1901"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huaimin WANG","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology","Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052307918","display_name":"Gang Yin","orcid":"https://orcid.org/0000-0002-0839-242X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang YIN","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology","Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078272955","display_name":"Cheng Yang","orcid":"https://orcid.org/0000-0002-4782-1645"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng YANG","raw_affiliation_strings":["Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology","Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology#TAB#"],"affiliations":[{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology#TAB#","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100331090","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-9059-4759"},"institutions":[{"id":"https://openalex.org/I125749732","display_name":"Western University","ror":"https://ror.org/02grkyz14","country_code":"CA","type":"education","lineage":["https://openalex.org/I125749732"]},{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CA","CN"],"is_corresponding":false,"raw_author_name":"Xiang LI","raw_affiliation_strings":["Department of Computer Science, The University of Western Ontario","Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Western Ontario","institution_ids":["https://openalex.org/I125749732"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010898755","display_name":"Peng Zou","orcid":"https://orcid.org/0000-0002-8484-5769"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng ZOU","raw_affiliation_strings":["Academy of Equipment"],"affiliations":[{"raw_affiliation_string":"Academy of Equipment","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100453601"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.8181,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83583633,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"E97.D","issue":"9","first_page":"2386","last_page":"2397"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9995999932289124,"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":0.9995999932289124,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980999827384949,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8698277473449707},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.7989515066146851},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5747859477996826},{"id":"https://openalex.org/keywords/software-development","display_name":"Software development","score":0.549828052520752},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5488281846046448},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5023243427276611},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4879853129386902},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.4719216823577881},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4640350341796875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4435707628726959},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.43002206087112427},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.42863228917121887},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2651239037513733},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22259020805358887},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.0974290668964386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8698277473449707},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.7989515066146851},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5747859477996826},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.549828052520752},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5488281846046448},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5023243427276611},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4879853129386902},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.4719216823577881},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4640350341796875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4435707628726959},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.43002206087112427},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.42863228917121887},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2651239037513733},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22259020805358887},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0974290668964386}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1587/transinf.2014edp7007","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7007","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/9/E97.D_2014EDP7007/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1587/transinf.2014edp7007","is_oa":true,"landing_page_url":"https://doi.org/10.1587/transinf.2014edp7007","pdf_url":"https://www.jstage.jst.go.jp/article/transinf/E97.D/9/E97.D_2014EDP7007/_pdf","source":{"id":"https://openalex.org/S2486202937","display_name":"IEICE Transactions on Information and Systems","issn_l":"0916-8532","issn":["0916-8532","1745-1361"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4320800604","host_organization_name":"Institute of Electronics, Information and Communication Engineers","host_organization_lineage":["https://openalex.org/P4320800604"],"host_organization_lineage_names":["Institute of Electronics, Information and Communication Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEICE Transactions on Information and Systems","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1121271761","display_name":null,"funder_award_id":"Program","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1749389203","display_name":null,"funder_award_id":"2012AA011201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1776922383","display_name":null,"funder_award_id":"A011201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2087396116","display_name":null,"funder_award_id":"China","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2662615474","display_name":null,"funder_award_id":"60903043","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3085993365","display_name":null,"funder_award_id":"(Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3317480652","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5939423041","display_name":null,"funder_award_id":"Technology","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7726157001","display_name":null,"funder_award_id":"Grant No.","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2142098106.pdf","grobid_xml":"https://content.openalex.org/works/W2142098106.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W66763315","https://openalex.org/W1965260616","https://openalex.org/W1986535241","https://openalex.org/W1994558922","https://openalex.org/W1998899601","https://openalex.org/W2015455557","https://openalex.org/W2044428238","https://openalex.org/W2046830558","https://openalex.org/W2050136587","https://openalex.org/W2057958729","https://openalex.org/W2063384185","https://openalex.org/W2073830447","https://openalex.org/W2114763031","https://openalex.org/W2116907335","https://openalex.org/W2120020585","https://openalex.org/W2125980283","https://openalex.org/W2143682573","https://openalex.org/W2146241755","https://openalex.org/W2150766729","https://openalex.org/W2150775529","https://openalex.org/W2165401136","https://openalex.org/W2170982140","https://openalex.org/W2497384426","https://openalex.org/W2744136779","https://openalex.org/W4240398231","https://openalex.org/W4243874760"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2623658258","https://openalex.org/W2143413548","https://openalex.org/W1969219540","https://openalex.org/W2370459448","https://openalex.org/W2105067402"],"abstract_inverted_index":{"The":[0,157],"large":[1],"amounts":[2],"of":[3,18,23,32,73,126],"freely":[4],"available":[5],"open":[6],"source":[7,60,196],"software":[8,19,30,37,56,82,103,210],"over":[9],"the":[10,15,24,172,225],"Internet":[11],"are":[12,140,146],"fundamentally":[13],"changing":[14],"traditional":[16],"paradigms":[17],"development.":[20],"Efficient":[21],"categorization":[22,57,90,114,218],"massive":[25],"projects":[26,74,104,153],"for":[27,35,206],"retrieving":[28],"relevant":[29],"is":[31,203],"vital":[33],"importance":[34],"Internet-based":[36,81],"development":[38,83],"such":[39],"as":[40],"solution":[41],"searching,":[42],"best":[43],"practices":[44],"learning":[45],"and":[46,88,116,136,142,183,208,228],"so":[47],"on.":[48],"Many":[49],"previous":[50,173],"works":[51],"have":[52],"been":[53],"conducted":[54],"on":[55,68,106,149],"by":[58,166],"mining":[59],"code":[61,197],"or":[62,78,198],"byte":[63,199],"code,":[64,200],"but":[65],"were":[66],"verified":[67],"only":[69],"relatively":[70],"small":[71],"collections":[72],"with":[75,180,187,220],"coarse-grained":[76],"categories":[77],"clusters.":[79],"However,":[80],"requires":[84],"finer-grained,":[85],"more":[86,150,181,188,204],"scalable":[87],"language-independent":[89,209],"approaches.":[91],"In":[92,212],"this":[93],"paper,":[94],"we":[95],"propose":[96],"a":[97,112,118],"novel":[98],"approach":[99,162,176,202],"to":[100,122,171],"hierarchically":[101],"categorize":[102],"based":[105],"their":[107],"online":[108],"profiles.":[109],"We":[110],"design":[111],"SVM-based":[113],"framework":[115],"adopt":[117],"weighted":[119,168],"combination":[120],"strategy":[121],"aggregate":[123],"different":[124],"types":[125],"profile":[127],"attributes":[128],"from":[129],"multiple":[130],"repositories.":[131,156],"Different":[132],"basic":[133],"classification":[134],"algorithms":[135],"feature":[137],"selection":[138],"techniques":[139],"employed":[141],"compared.":[143],"Extensive":[144],"experiments":[145,214],"carried":[147],"out":[148],"than":[151,189],"21,000":[152],"across":[154],"five":[155],"results":[158,179],"show":[159],"that":[160,194,216],"our":[161,175,201],"achieves":[163],"significant":[164],"improvements":[165],"using":[167],"combination.":[169],"Compared":[170],"work,":[174],"presents":[177],"competitive":[178],"finer-grained":[182],"multi-layered":[184],"category":[185],"hierarchy":[186],"120":[190],"categories.":[191],"Unlike":[192],"approaches":[193],"use":[195],"effective":[205],"large-scale":[207],"categorization.":[211],"addition,":[213],"suggest":[215],"hierarchical":[217],"combined":[219],"general":[221],"keyword-based":[222],"searching":[223],"improves":[224],"retrieval":[226],"efficiency":[227],"accuracy.":[229]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}