{"id":"https://openalex.org/W2089132504","doi":"https://doi.org/10.5626/jcse.2009.3.3.165","title":"HKIB-20000 &amp; HKIB-40075: Hangul Benchmark Collections for Text Categorization Research","display_name":"HKIB-20000 &amp; HKIB-40075: Hangul Benchmark Collections for Text Categorization Research","publication_year":2009,"publication_date":"2009-09-30","ids":{"openalex":"https://openalex.org/W2089132504","doi":"https://doi.org/10.5626/jcse.2009.3.3.165","mag":"2089132504"},"language":"en","primary_location":{"id":"doi:10.5626/jcse.2009.3.3.165","is_oa":true,"landing_page_url":"https://doi.org/10.5626/jcse.2009.3.3.165","pdf_url":"http://koreascience.or.kr:80/article/JAKO200934939600246.pdf","source":{"id":"https://openalex.org/S2764945857","display_name":"Journal of Computing Science and Engineering","issn_l":"1976-4677","issn":["1976-4677","2093-8020"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computing Science and Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"http://koreascience.or.kr:80/article/JAKO200934939600246.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103237572","display_name":"Jin-Suk Kim","orcid":"https://orcid.org/0000-0003-0734-8707"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jin-Suk Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064860288","display_name":"Ho-Seop Choe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ho-Seop Choe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049904665","display_name":"Beom-Jong You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Beom-Jong You","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100523287","display_name":"Jeong\u2010Hyun Seo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeong-Hyun Seo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042025844","display_name":"Suk-Hoon Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suk-Hoon Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5072680355","display_name":"Dong-Yul Ra","orcid":"https://orcid.org/0000-0003-1449-4614"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong-Yul Ra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103237572"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9054,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80790724,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3","issue":"3","first_page":"165","last_page":"180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9901000261306763,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9864000082015991,"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/categorization","display_name":"Categorization","score":0.8257217407226562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8210635781288147},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6999841332435608},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.667041540145874},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.5493721961975098},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5432078242301941},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.46423855423927307},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4470939040184021},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4460224509239197},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3232004642486572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2989538609981537}],"concepts":[{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.8257217407226562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8210635781288147},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6999841332435608},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.667041540145874},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.5493721961975098},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5432078242301941},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.46423855423927307},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4470939040184021},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4460224509239197},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3232004642486572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2989538609981537},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5626/jcse.2009.3.3.165","is_oa":true,"landing_page_url":"https://doi.org/10.5626/jcse.2009.3.3.165","pdf_url":"http://koreascience.or.kr:80/article/JAKO200934939600246.pdf","source":{"id":"https://openalex.org/S2764945857","display_name":"Journal of Computing Science and Engineering","issn_l":"1976-4677","issn":["1976-4677","2093-8020"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computing Science and Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5626/jcse.2009.3.3.165","is_oa":true,"landing_page_url":"https://doi.org/10.5626/jcse.2009.3.3.165","pdf_url":"http://koreascience.or.kr:80/article/JAKO200934939600246.pdf","source":{"id":"https://openalex.org/S2764945857","display_name":"Journal of Computing Science and Engineering","issn_l":"1976-4677","issn":["1976-4677","2093-8020"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computing Science and Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.800000011920929}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2089132504.pdf"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1482260847","https://openalex.org/W2005422315","https://openalex.org/W2041383412","https://openalex.org/W2071664212","https://openalex.org/W2079557131","https://openalex.org/W2114535528","https://openalex.org/W2118020653","https://openalex.org/W2126502509","https://openalex.org/W2141834653","https://openalex.org/W2150102617","https://openalex.org/W2160484851","https://openalex.org/W2435251607"],"related_works":["https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2390698788","https://openalex.org/W2078570174","https://openalex.org/W2035261173","https://openalex.org/W2125109223","https://openalex.org/W2383063829","https://openalex.org/W2082678934","https://openalex.org/W2138922887"],"abstract_inverted_index":{"The":[0,21],"HKIB,":[1],"or":[2,17,114],"Hankookilbo,":[3],"test":[4,80,97,131],"collections":[5],"are":[6],"two":[7],"archives":[8],"of":[9,147],"Korean":[10,164],"newswire":[11,23,92],"stories":[12,24,51,93],"manually":[13,47],"categorized":[14],"with":[15,52],"semi-hierarchical":[16,55],"hierarchical":[18,107],"category":[19,69],"taxonomies.":[20],"base":[22],"were":[25],"made":[26],"available":[27],"by":[28,54],"the":[29,95,101,148],"Hankook":[30],"Ilbo":[31],"(The":[32],"Korea":[33],"Daily)":[34],"for":[35,153,160],"research":[36,162],"purposes.":[37],"At":[38],"first,":[39],"Chungnam":[40],"National":[41],"University":[42,85],"and":[43,56,86,110,142,156],"KISTI":[44,87],"collaborated":[45,88],"to":[46,73,89,99,104,111,117,124],"tag":[48],"40,075":[49],"news":[50,63,119],"categories":[53,116],"balanced":[57],"three-level":[58],"classification":[59,102],"scheme,":[60],"where":[61],"each":[62,118],"story":[64,120],"has":[65],"only":[66],"one":[67,113],"level-3":[68],"(single-labeling).":[70],"We":[71,122,133],"refer":[72,123],"this":[74,125],"original":[75],"data":[76,127],"set":[77,128],"as":[78,129],"HKIB-40075":[79,96],"collection.":[81,132],"And":[82],"then":[83],"Yonsei":[84],"select":[90],"20,000":[91],"from":[94],"collection,":[98],"rearrange":[100],"scheme":[103],"be":[105],"fully":[106],"but":[108],"unbalanced,":[109],"assign":[112],"more":[115],"(multi-labeling).":[121],"modified":[126],"HKIB-20000":[130,141],"benchmark":[134],"a":[135],"k-NN":[136],"categorization":[137,166],"algorithm":[138],"both":[139],"on":[140,143,163],"HKIB-40075,":[144],"illustrating":[145],"properties":[146],"collections,":[149],"providing":[150],"baseline":[151],"results":[152],"future":[154],"studies,":[155],"suggesting":[157],"new":[158],"directions":[159],"further":[161],"text":[165],"problem.":[167]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-22T06:13:13.366637","created_date":"2025-10-10T00:00:00"}
