{"id":"https://openalex.org/W2148202334","doi":"https://doi.org/10.1177/016555150302900204","title":"Developing a specialized directory system by automatically classifying Web documents","display_name":"Developing a specialized directory system by automatically classifying Web documents","publication_year":2003,"publication_date":"2003-04-01","ids":{"openalex":"https://openalex.org/W2148202334","doi":"https://doi.org/10.1177/016555150302900204","mag":"2148202334"},"language":"en","primary_location":{"id":"doi:10.1177/016555150302900204","is_oa":false,"landing_page_url":"https://doi.org/10.1177/016555150302900204","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-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/A5112425523","display_name":"Young Mee Chung","orcid":null},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Young Mee Chung","raw_affiliation_strings":["Yonsei University, Seoul, South Korea,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yonsei University, Seoul, South Korea,","institution_ids":["https://openalex.org/I193775966"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014968466","display_name":"Younghee Noh","orcid":"https://orcid.org/0000-0002-0046-4038"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Young-Hee Noh","raw_affiliation_strings":["Ewha Womans University, Seoul, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ewha Womans University, Seoul, South Korea","institution_ids":["https://openalex.org/I138925566"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112425523"],"corresponding_institution_ids":["https://openalex.org/I193775966"],"apc_list":null,"apc_paid":null,"fwci":0.9372,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.82328279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"29","issue":"2","first_page":"117","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9882000088691711,"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":0.9868999719619751,"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/directory","display_name":"Directory","score":0.8513957262039185},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8114785552024841},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.647546648979187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5559438467025757},{"id":"https://openalex.org/keywords/classification-scheme","display_name":"Classification scheme","score":0.5425795316696167},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.5208950042724609},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49595651030540466},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.4494374692440033},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37564563751220703},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3513599634170532},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2788620591163635}],"concepts":[{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.8513957262039185},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8114785552024841},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.647546648979187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5559438467025757},{"id":"https://openalex.org/C13460635","wikidata":"https://www.wikidata.org/wiki/Q85753676","display_name":"Classification scheme","level":2,"score":0.5425795316696167},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.5208950042724609},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49595651030540466},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.4494374692440033},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37564563751220703},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3513599634170532},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2788620591163635},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/016555150302900204","is_oa":false,"landing_page_url":"https://doi.org/10.1177/016555150302900204","pdf_url":null,"source":{"id":"https://openalex.org/S68913162","display_name":"Journal of Information Science","issn_l":"0165-5515","issn":["0165-5515","1741-6485"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1608864735","https://openalex.org/W1981697855","https://openalex.org/W2005422315","https://openalex.org/W2100958137","https://openalex.org/W2114535528","https://openalex.org/W2435251607"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W3115906952","https://openalex.org/W3134811395","https://openalex.org/W3155196058","https://openalex.org/W3120732231","https://openalex.org/W2411463128","https://openalex.org/W4313035775","https://openalex.org/W2900292107","https://openalex.org/W1594995750","https://openalex.org/W1995014490"],"abstract_inverted_index":{"This":[0,142],"study":[1],"developed":[2],"a":[3,53,86,123,132,137,155,159,163],"specialized":[4],"directory":[5,31],"system":[6],"using":[7,103],"an":[8],"automatic":[9],"classification":[10,21,27,77,151],"technique.":[11],"Economics":[12],"was":[13],"selected":[14,46],"as":[15],"the":[16,20,30,33,48,61,72,76,95,104,150],"subject":[17,36,43,91],"field":[18],"for":[19],"experiments":[22,102],"with":[23],"Web":[24,62,79],"documents.":[25],"The":[26,98,119],"scheme":[28],"of":[29,88,114,140],"follows":[32],"DDC,":[34],"and":[35,59,100,116,162],"terms":[37],"representing":[38],"each":[39],"class":[40],"number":[41],"or":[42],"category":[44],"were":[45,66,83],"from":[47,94],"DDC":[49,96],"table":[50],"to":[51,70,148],"construct":[52],"representative":[54,105],"term":[55,106],"dictionary.":[56],"In":[57,75],"collecting":[58],"classifying":[60],"documents,":[63],"various":[64],"strategies":[65],"tested":[67],"in":[68,81,109,131],"order":[69],"find":[71],"optimal":[73],"thresholds.":[74],"experiments,":[78],"documents":[80],"economics":[82],"classified":[84],"into":[85],"total":[87],"757":[89],"hierarchical":[90],"categories":[92],"built":[93],"scheme.":[97],"first":[99],"second":[101],"dictionary":[107],"resulted":[108],"relatively":[110],"high":[111],"precision":[112,138],"ratios":[113],"77":[115],"60%,":[117],"respectively.":[118],"third":[120],"experiment":[121],"employing":[122],"machine":[124],"learning-based":[125],"k":[126],"-nearest":[127],"neighbours":[128],"(kNN)":[129],"classifier":[130],"closed":[133],"experimental":[134],"setting":[135],"achieved":[136],"ratio":[139],"96%.":[141],"implies":[143],"that":[144],"it":[145],"is":[146],"possible":[147],"enhance":[149],"performance":[152],"by":[153],"applying":[154],"hybrid":[156],"method":[157],"combining":[158],"dictionary-based":[160],"technique":[161],"kNN":[164],"classifier.":[165]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-05-05T06:06:40.768181","created_date":"2025-10-10T00:00:00"}