{"id":"https://openalex.org/W2048866481","doi":"https://doi.org/10.1142/s0219427903000802","title":"Hierarchical Categorization Based on k-Nearest Neighbor Approach for Web Site Classification","display_name":"Hierarchical Categorization Based on k-Nearest Neighbor Approach for Web Site Classification","publication_year":2003,"publication_date":"2003-03-01","ids":{"openalex":"https://openalex.org/W2048866481","doi":"https://doi.org/10.1142/s0219427903000802","mag":"2048866481"},"language":"en","primary_location":{"id":"doi:10.1142/s0219427903000802","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427903000802","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","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/A5056526024","display_name":"Oh\u2010Woog Kwon","orcid":"https://orcid.org/0000-0002-5904-2358"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"OH-WOOG KWON","raw_affiliation_strings":["Natural Language Processing Laboratory, UNISOFT CO., Ltd., 7th Floor Sejung Building, 1126-3 Guwol 1-dong Namdong-gu, Incheon, 405-221, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Natural Language Processing Laboratory, UNISOFT CO., Ltd., 7th Floor Sejung Building, 1126-3 Guwol 1-dong Namdong-gu, Incheon, 405-221, Korea","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5056526024"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11705137,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"01","first_page":"63","last_page":"85"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9983999729156494,"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":0.9983999729156494,"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":0.9962000250816345,"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":0.9822999835014343,"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":0.8313156366348267},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6703994274139404},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6564072966575623},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6102854013442993},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.5703745484352112},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5567408800125122},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.5508373975753784},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.5250158905982971},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45712795853614807},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4026591181755066},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3515169322490692},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3264150619506836},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.3005043864250183},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.2640908360481262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8313156366348267},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6703994274139404},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6564072966575623},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6102854013442993},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.5703745484352112},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5567408800125122},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.5508373975753784},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.5250158905982971},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45712795853614807},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4026591181755066},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3515169322490692},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3264150619506836},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.3005043864250183},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.2640908360481262},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219427903000802","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219427903000802","pdf_url":null,"source":{"id":"https://openalex.org/S50006202","display_name":"International Journal of Computer Processing Of Languages","issn_l":"1793-8406","issn":["1793-8406","2010-0205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Processing of Languages","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.544.276","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.544.276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mti.ugm.ac.id/~adji/courses/resources/doctor/WorldSci/2003/k-NearestWebClassify03.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1487445520","https://openalex.org/W1523949738","https://openalex.org/W1550206324","https://openalex.org/W1594962278","https://openalex.org/W1833785989","https://openalex.org/W1988711048","https://openalex.org/W1989568037","https://openalex.org/W2005422315","https://openalex.org/W2035754578","https://openalex.org/W2063198646","https://openalex.org/W2063862666","https://openalex.org/W2079672501","https://openalex.org/W2094400120","https://openalex.org/W2094934653","https://openalex.org/W2096411881","https://openalex.org/W2107008379","https://openalex.org/W2110224739","https://openalex.org/W2114535528","https://openalex.org/W2149684865"],"related_works":["https://openalex.org/W1541158057","https://openalex.org/W2083329789","https://openalex.org/W2268257560","https://openalex.org/W2626548695","https://openalex.org/W2030268420","https://openalex.org/W2017818230","https://openalex.org/W2548348270","https://openalex.org/W2885559332","https://openalex.org/W1519586109","https://openalex.org/W2982387199"],"abstract_inverted_index":{"Automatic":[0],"categorization":[1,27],"is":[2,45,59,151],"a":[3,51,55,60,71,110,125,154,179],"viable":[4],"method":[5,129,187],"to":[6,23,29,84,115,169],"deal":[7],"with":[8,50,199],"the":[9,13,39,42,88,97,103,116,143,146,158,173,184],"scaling":[10],"problem":[11],"on":[12,131,178],"World":[14],"Wide":[15],"Web.":[16],"In":[17,176],"this":[18,100],"paper,":[19],"we":[20,123],"consider":[21],"how":[22],"apply":[24],"general":[25],"text":[26],"techniques":[28],"Web":[30,56,63,68,85,106,126,140,182],"site":[31,127],"classification":[32,128,186],"tasks.":[33],"Two":[34],"relevant":[35],"issues":[36],"concern,":[37],"first,":[38],"case":[40],"where":[41],"classifying":[43],"object":[44],"not":[46],"one":[47],"document,":[48],"as":[49,134,136],"home":[52,111,117],"page,":[53],"but":[54,157],"site,":[57],"which":[58,76],"collection":[61],"of":[62,105,139,149,165,172,192],"pages.":[64],"Second,":[65],"real":[66],"world":[67],"directories":[69],"have":[70],"complex":[72],"hierarchical":[73,89,147,174],"structure,":[74,156],"in":[75,92,113],"leaf":[77],"and":[78],"non-leaf":[79],"categories":[80,168],"are":[81],"directly":[82],"assigned":[83],"sites,":[86],"unlike":[87],"structure":[90,148],"treated":[91],"most":[93],"previous":[94],"research.":[95],"On":[96,142],"first":[98],"issue,":[99,145],"paper":[101],"proposes":[102],"use":[104],"pages":[107],"linked":[108],"by":[109,196],"page":[112,118],"addition":[114],"itself.":[119],"To":[120],"accomplish":[121],"this,":[122],"propose":[124],"based":[130],"connectivity":[132],"analysis,":[133],"well":[135],"content":[137],"analysis":[138],"sites.":[141],"second":[144],"classifiers":[150],"transformed":[152],"into":[153],"flattened":[155],"classifier":[159],"for":[160],"each":[161],"category":[162],"uses":[163],"features":[164],"its":[166],"next-of-kin":[167],"take":[170],"advantage":[171],"relationship.":[175],"experiments":[177],"Korean":[180],"commercial":[181],"directory,":[183],"proposed":[185],"achieved":[188],"an":[189,200],"amazing":[190],"improvement":[191],"micro-averaging":[193],"breakeven":[194],"point":[195],"36.6%,":[197],"compared":[198],"ordinary":[201],"classifier.":[202]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
