{"id":"https://openalex.org/W2345381140","doi":"https://doi.org/10.1080/13614568.2016.1152316","title":"An efficient scheme for automatic web pages categorization using the support vector machine","display_name":"An efficient scheme for automatic web pages categorization using the support vector machine","publication_year":2016,"publication_date":"2016-05-04","ids":{"openalex":"https://openalex.org/W2345381140","doi":"https://doi.org/10.1080/13614568.2016.1152316","mag":"2345381140"},"language":"en","primary_location":{"id":"doi:10.1080/13614568.2016.1152316","is_oa":false,"landing_page_url":"https://doi.org/10.1080/13614568.2016.1152316","pdf_url":null,"source":{"id":"https://openalex.org/S5817663","display_name":"New Review of Hypermedia and Multimedia","issn_l":"0955-8543","issn":["0955-8543","1361-4568","1740-7842"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"New Review of Hypermedia and Multimedia","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/A5113499634","display_name":"Vinod K. Bhalla","orcid":null},"institutions":[{"id":"https://openalex.org/I162030827","display_name":"Thapar Institute of Engineering & Technology","ror":"https://ror.org/00wdq3744","country_code":"IN","type":"education","lineage":["https://openalex.org/I162030827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinod Kumar Bhalla","raw_affiliation_strings":["Department of Computer Science and Engineering, Thapar University, Patiala, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Thapar University, Patiala, Punjab, India","institution_ids":["https://openalex.org/I162030827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409306","display_name":"Neeraj Kumar","orcid":"https://orcid.org/0000-0002-3020-3947"},"institutions":[{"id":"https://openalex.org/I162030827","display_name":"Thapar Institute of Engineering & Technology","ror":"https://ror.org/00wdq3744","country_code":"IN","type":"education","lineage":["https://openalex.org/I162030827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Neeraj Kumar","raw_affiliation_strings":["Department of Computer Science and Engineering, Thapar University, Patiala, Punjab, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Thapar University, Patiala, Punjab, India","institution_ids":["https://openalex.org/I162030827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100409306"],"corresponding_institution_ids":["https://openalex.org/I162030827"],"apc_list":null,"apc_paid":null,"fwci":6.3117,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.96353224,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"22","issue":"3","first_page":"223","last_page":"242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9990000128746033,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9973999857902527,"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":0.9926999807357788,"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/scheme","display_name":"Scheme (mathematics)","score":0.800218403339386},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7083221077919006},{"id":"https://openalex.org/keywords/categorization","display_name":"Categorization","score":0.6893374919891357},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5975595116615295},{"id":"https://openalex.org/keywords/text-categorization","display_name":"Text categorization","score":0.4633994400501251},{"id":"https://openalex.org/keywords/classification-scheme","display_name":"Classification scheme","score":0.41973087191581726},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.39906516671180725},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37161487340927124},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3535171151161194},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32601404190063477},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08886644244194031}],"concepts":[{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.800218403339386},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7083221077919006},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.6893374919891357},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5975595116615295},{"id":"https://openalex.org/C2986744138","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Text categorization","level":3,"score":0.4633994400501251},{"id":"https://openalex.org/C13460635","wikidata":"https://www.wikidata.org/wiki/Q85753676","display_name":"Classification scheme","level":2,"score":0.41973087191581726},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39906516671180725},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37161487340927124},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3535171151161194},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32601404190063477},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08886644244194031},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1080/13614568.2016.1152316","is_oa":false,"landing_page_url":"https://doi.org/10.1080/13614568.2016.1152316","pdf_url":null,"source":{"id":"https://openalex.org/S5817663","display_name":"New Review of Hypermedia and Multimedia","issn_l":"0955-8543","issn":["0955-8543","1361-4568","1740-7842"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"New Review of Hypermedia and Multimedia","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":35,"referenced_works":["https://openalex.org/W1482260847","https://openalex.org/W1855811457","https://openalex.org/W2007395264","https://openalex.org/W2017023378","https://openalex.org/W2023374068","https://openalex.org/W2038029738","https://openalex.org/W2049488566","https://openalex.org/W2050399271","https://openalex.org/W2051391088","https://openalex.org/W2053699633","https://openalex.org/W2055500683","https://openalex.org/W2058435344","https://openalex.org/W2061809273","https://openalex.org/W2063862666","https://openalex.org/W2065584379","https://openalex.org/W2066636486","https://openalex.org/W2067223933","https://openalex.org/W2067976963","https://openalex.org/W2076008912","https://openalex.org/W2087347434","https://openalex.org/W2092689128","https://openalex.org/W2102867086","https://openalex.org/W2111689752","https://openalex.org/W2118201046","https://openalex.org/W2119821739","https://openalex.org/W2133239529","https://openalex.org/W2146796518","https://openalex.org/W2147898188","https://openalex.org/W2150827944","https://openalex.org/W2153635508","https://openalex.org/W2155064424","https://openalex.org/W2164565864","https://openalex.org/W2503755628","https://openalex.org/W2999905431","https://openalex.org/W4239381793"],"related_works":["https://openalex.org/W2484602794","https://openalex.org/W2360898036","https://openalex.org/W2390857744","https://openalex.org/W2133651098","https://openalex.org/W2113616822","https://openalex.org/W2390698788","https://openalex.org/W4236420972","https://openalex.org/W2383063829","https://openalex.org/W2138922887","https://openalex.org/W2082678934"],"abstract_inverted_index":{"In":[0,123],"the":[1,9,14,17,31,71,76,103,112,120,124,138,153,159,165,176,189,195,254,261,264],"past":[2],"few":[3],"years,":[4],"with":[5,242],"an":[6,46,97],"evolution":[7],"of":[8,16,35,45,49,55,58,70,85,114,119,131,143,158,178,197,199,206,263,269,275],"Internet":[10,18,32],"and":[11,116,129,170,208,245],"related":[12],"technologies,":[13],"number":[15],"users":[19,23],"grows":[20],"exponentially.":[21],"These":[22],"demand":[24],"access":[25],"to":[26,61,213,224],"relevant":[27,117],"web":[28,50,59,99,121,145,160,276],"pages":[29,60,100],"from":[30],"within":[33],"fraction":[34],"seconds.":[36],"To":[37,90],"achieve":[38,62,91,214],"this":[39,94],"goal,":[40],"there":[41],"is":[42,65,109,162,192,211,222],"a":[43,66,215,226,236],"requirement":[44],"efficient":[47],"categorization":[48,54,101,142],"page":[51,161],"contents.":[52],"Manual":[53],"these":[56,81,92],"billions":[57],"high":[63],"accuracy":[64,86,271],"challenging":[67],"task.":[68],"Most":[69],"existing":[72],"techniques":[73],"reported":[74],"in":[75,164,201,240,267,272],"literature":[77],"are":[78,133,173],"semi-automatic.":[79],"Using":[80],"techniques,":[82],"higher":[83,216],"level":[84],"cannot":[87],"be":[88],"achieved.":[89],"goals,":[93],"paper":[95],"proposes":[96],"automatic":[98],"into":[102],"domain":[104,144,186],"category.":[105],"The":[106,230,257],"proposed":[107,125,166,231,265],"scheme":[108,232,266],"based":[110,151,174],"on":[111,152,175,194],"identification":[113],"specific":[115],"features":[118,132],"pages.":[122,146,187,277],"scheme,":[126],"first":[127],"extraction":[128,149,169,244],"evaluation":[130],"done":[134,212],"followed":[135],"by":[136,183],"filtering":[137],"feature":[139,148,220,243],"set":[140,221],"for":[141],"A":[147],"tool":[150],"HTML":[154],"document":[155],"object":[156],"model":[157],"developed":[163,182],"scheme.":[167],"Feature":[168],"weight":[171],"assignment":[172],"collection":[177],"domain-specific":[179],"keyword":[180,190,202],"list":[181,191],"considering":[184],"various":[185],"Moreover,":[188],"reduced":[193],"basis":[196],"ids":[198],"keywords":[200,207],"list.":[203],"Also,":[204],"stemming":[205],"tag":[209],"text":[210],"accuracy.":[217],"An":[218],"extensive":[219],"generated":[223],"develop":[225],"robust":[227],"classification":[228,255],"technique.":[229],"was":[233],"evaluated":[234],"using":[235,248],"machine":[237,251],"learning":[238],"method":[239],"combination":[241],"statistical":[246],"analysis":[247],"support":[249],"vector":[250],"kernel":[252],"as":[253],"tool.":[256],"results":[258],"obtained":[259],"confirm":[260],"effectiveness":[262],"terms":[268],"its":[270],"different":[273],"categories":[274]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}