{"id":"https://openalex.org/W2155064424","doi":"https://doi.org/10.1109/icsmc.2004.1401147","title":"An empirical study for hypertext categorization","display_name":"An empirical study for hypertext categorization","publication_year":2005,"publication_date":"2005-03-31","ids":{"openalex":"https://openalex.org/W2155064424","doi":"https://doi.org/10.1109/icsmc.2004.1401147","mag":"2155064424"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2004.1401147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1401147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","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/A5065627637","display_name":"Houda Benbrahim","orcid":"https://orcid.org/0009-0005-2797-212X"},"institutions":[{"id":"https://openalex.org/I63072094","display_name":"University of Portsmouth","ror":"https://ror.org/03ykbk197","country_code":"GB","type":"education","lineage":["https://openalex.org/I63072094"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"H. Benbrahim","raw_affiliation_strings":["Department of Computer Science & Software Engineering, Portsmouth University, Portsmouth, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Software Engineering, Portsmouth University, Portsmouth, UK","institution_ids":["https://openalex.org/I63072094"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112240698","display_name":"Max Bramer","orcid":null},"institutions":[{"id":"https://openalex.org/I63072094","display_name":"University of Portsmouth","ror":"https://ror.org/03ykbk197","country_code":"GB","type":"education","lineage":["https://openalex.org/I63072094"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M. Bramer","raw_affiliation_strings":["Department of Computer Science & Software Engineering, Portsmouth University, Portsmouth, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science & Software Engineering, Portsmouth University, Portsmouth, UK","institution_ids":["https://openalex.org/I63072094"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065627637"],"corresponding_institution_ids":["https://openalex.org/I63072094"],"apc_list":null,"apc_paid":null,"fwci":0.4387,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75379547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":"6","issue":null,"first_page":"5952","last_page":"5957"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9991999864578247,"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":0.9991999864578247,"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/T11644","display_name":"Spam and Phishing Detection","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980000257492065,"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":0.8324909210205078},{"id":"https://openalex.org/keywords/hypertext","display_name":"Hypertext","score":0.8067552447319031},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.698995053768158},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.666813850402832},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.5933458209037781},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5698447227478027},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.49339500069618225},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.44853076338768005},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4476536512374878},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4387699365615845},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.43210363388061523},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.41649091243743896},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3975025415420532},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3662417232990265}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324909210205078},{"id":"https://openalex.org/C162215914","wikidata":"https://www.wikidata.org/wiki/Q93241","display_name":"Hypertext","level":2,"score":0.8067552447319031},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.698995053768158},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.666813850402832},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.5933458209037781},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5698447227478027},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.49339500069618225},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.44853076338768005},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4476536512374878},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4387699365615845},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.43210363388061523},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.41649091243743896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3975025415420532},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3662417232990265},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2004.1401147","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2004.1401147","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7900000214576721,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1518603657","https://openalex.org/W1532285064","https://openalex.org/W1605217017","https://openalex.org/W1978394996","https://openalex.org/W2007395264","https://openalex.org/W2043747172","https://openalex.org/W2043772506","https://openalex.org/W2092689128","https://openalex.org/W2094934653","https://openalex.org/W2149684865","https://openalex.org/W2325227998","https://openalex.org/W2435251607","https://openalex.org/W6631035069","https://openalex.org/W6631855669","https://openalex.org/W6651935896","https://openalex.org/W6674019326","https://openalex.org/W6682304300","https://openalex.org/W6717827561"],"related_works":["https://openalex.org/W2165912799","https://openalex.org/W2735662278","https://openalex.org/W2392768766","https://openalex.org/W2058118494","https://openalex.org/W2382615723","https://openalex.org/W4311804456","https://openalex.org/W1987484445","https://openalex.org/W2501188010","https://openalex.org/W1536970214","https://openalex.org/W2095118173"],"abstract_inverted_index":{"As":[0],"the":[1,5,20,93,102,131,144,157,160],"Web":[2],"expands":[3],"exponentially,":[4],"need":[6],"to":[7,11,30,75,87,91,99,129],"put":[8],"some":[9],"order":[10],"its":[12],"content":[13,147],"becomes":[14],"apparent.":[15],"Hypertext":[16],"categorization,":[17],"that":[18,34,60,142],"is":[19,61],"automatic":[21,48],"classification":[22,94,161],"of":[23,106,108,159],"web":[24],"documents":[25,78],"into":[26,89],"predefined":[27],"classes,":[28],"came":[29],"elevate":[31],"humans":[32],"from":[33],"task.":[35],"The":[36,139],"extra":[37,81],"information":[38,56,82],"available":[39,63],"in":[40,64,84],"a":[41],"hypertext":[42,58,111],"document":[43],"poses":[44],"new":[45],"challenges":[46],"for":[47,57,77],"categorization.":[49],"HTML":[50,85,149],"tags":[51],"and":[52,79,96,113,125,153],"metadata":[53],"provide":[54],"rich":[55],"categorization":[59],"not":[62],"traditional":[65],"text":[66,133,146],"classification.":[67],"This":[68],"paper":[69],"looks":[70],"at":[71],"(i)":[72],"what":[73],"representation":[74,134],"use":[76],"which":[80],"hidden":[83],"pages":[86],"take":[88],"consideration":[90],"improve":[92],"task,":[95],"(ii)":[97],"how":[98],"deal":[100],"with":[101,136,148],"very":[103],"high":[104],"number":[105],"features":[107],"texts.":[109],"A":[110],"dataset":[112],"four":[114],"well-known":[115],"learning":[116],"algorithms":[117],"(Naive":[118],"Bayes,":[119],"K-nearest":[120],"neighbor,":[121],"support":[122],"vector":[123],"machines":[124],"C4.5)":[126],"were":[127],"used":[128],"exploit":[130],"enriched":[132],"along":[135],"feature":[137],"reduction.":[138],"results":[140],"showed":[141],"enhancing":[143],"basic":[145],"page":[150],"keywords,":[151],"title":[152],"anchor":[154],"links":[155],"improved":[156],"accuracy":[158],"algorithms.":[162]},"counts_by_year":[{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}