{"id":"https://openalex.org/W1436652029","doi":"https://doi.org/10.1177/0165551515591724","title":"Classifier and feature set ensembles for web page classification","display_name":"Classifier and feature set ensembles for web page classification","publication_year":2015,"publication_date":"2015-06-29","ids":{"openalex":"https://openalex.org/W1436652029","doi":"https://doi.org/10.1177/0165551515591724","mag":"1436652029"},"language":"en","primary_location":{"id":"doi:10.1177/0165551515591724","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551515591724","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/A5001374957","display_name":"Aytu\u011f Onan","orcid":"https://orcid.org/0000-0002-9434-5880"},"institutions":[{"id":"https://openalex.org/I16748637","display_name":"Manisa Celal Bayar University","ror":"https://ror.org/053f2w588","country_code":"TR","type":"education","lineage":["https://openalex.org/I16748637"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Aytu\u011f Onan","raw_affiliation_strings":["Celal Bayar University, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Celal Bayar University, Turkey","institution_ids":["https://openalex.org/I16748637"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5001374957"],"corresponding_institution_ids":["https://openalex.org/I16748637"],"apc_list":null,"apc_paid":null,"fwci":10.2392,"has_fulltext":false,"cited_by_count":121,"citation_normalized_percentile":{"value":0.98061676,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"42","issue":"2","first_page":"150","last_page":"165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9966999888420105,"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":0.9696000218391418,"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":0.7688931822776794},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.7255452871322632},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.692542314529419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6741433143615723},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.6386482119560242},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5756748914718628},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5553634166717529},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5536073446273804},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.5182654857635498},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48116716742515564},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.470711886882782},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.47068148851394653},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.4209461808204651},{"id":"https://openalex.org/keywords/adaboost","display_name":"AdaBoost","score":0.41422370076179504},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.38216105103492737},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1047261655330658}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688931822776794},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.7255452871322632},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.692542314529419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6741433143615723},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.6386482119560242},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5756748914718628},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5553634166717529},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5536073446273804},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.5182654857635498},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48116716742515564},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.470711886882782},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.47068148851394653},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.4209461808204651},{"id":"https://openalex.org/C141404830","wikidata":"https://www.wikidata.org/wiki/Q2823869","display_name":"AdaBoost","level":3,"score":0.41422370076179504},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.38216105103492737},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1047261655330658}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/0165551515591724","is_oa":false,"landing_page_url":"https://doi.org/10.1177/0165551515591724","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W28821909","https://openalex.org/W62915308","https://openalex.org/W187357405","https://openalex.org/W193838664","https://openalex.org/W251061919","https://openalex.org/W798049283","https://openalex.org/W1480254719","https://openalex.org/W1495061682","https://openalex.org/W1517228774","https://openalex.org/W1518660678","https://openalex.org/W1534344657","https://openalex.org/W1534477342","https://openalex.org/W1574206268","https://openalex.org/W1575403013","https://openalex.org/W1582036668","https://openalex.org/W1583061999","https://openalex.org/W1583837637","https://openalex.org/W1616283197","https://openalex.org/W1833977909","https://openalex.org/W1878305827","https://openalex.org/W1989993068","https://openalex.org/W1997113291","https://openalex.org/W2008342891","https://openalex.org/W2008638605","https://openalex.org/W2021137987","https://openalex.org/W2032304665","https://openalex.org/W2038029738","https://openalex.org/W2053699633","https://openalex.org/W2059586463","https://openalex.org/W2067223933","https://openalex.org/W2077430530","https://openalex.org/W2109676405","https://openalex.org/W2112076978","https://openalex.org/W2112943428","https://openalex.org/W2113242816","https://openalex.org/W2115449743","https://openalex.org/W2116509046","https://openalex.org/W2118020653","https://openalex.org/W2119387367","https://openalex.org/W2124868070","https://openalex.org/W2125055259","https://openalex.org/W2125085620","https://openalex.org/W2135018274","https://openalex.org/W2136222411","https://openalex.org/W2140190241","https://openalex.org/W2143455647","https://openalex.org/W2147169507","https://openalex.org/W2150827944","https://openalex.org/W2154529539","https://openalex.org/W2155806188","https://openalex.org/W2164400088","https://openalex.org/W2167101736","https://openalex.org/W2167917621","https://openalex.org/W2237794120","https://openalex.org/W2435251607","https://openalex.org/W2505921950","https://openalex.org/W2619610413","https://openalex.org/W2912934387","https://openalex.org/W2914859268","https://openalex.org/W2976840617","https://openalex.org/W4212883601","https://openalex.org/W4232557450","https://openalex.org/W4235927334","https://openalex.org/W4244238212","https://openalex.org/W4248018214","https://openalex.org/W4298892674"],"related_works":["https://openalex.org/W4382315444","https://openalex.org/W4233259193","https://openalex.org/W2600353413","https://openalex.org/W4390916549","https://openalex.org/W2915435096","https://openalex.org/W4381298925","https://openalex.org/W4285213578","https://openalex.org/W2097856925","https://openalex.org/W1997565450","https://openalex.org/W4298012357"],"abstract_inverted_index":{"Web":[0,33],"page":[1,34,43,89,182,203,237],"classification":[2,35,119],"is":[3,36,215,231],"an":[4],"important":[5],"research":[6,97],"direction":[7,98],"on":[8,17,50,156],"web":[9,19,30,42,58,64,66,84,88,181,202,236],"mining.":[10],"The":[11,171,184],"abundant":[12],"amount":[13],"of":[14,39,130,177,199,220,261],"data":[15,75],"available":[16],"the":[18,37,174,196,206,209,218],"makes":[20],"it":[21],"essential":[22],"to":[23,44,104],"develop":[24],"efficient":[25],"and":[26,69,74,139,143,152,168,191,226,244,249,251],"robust":[27,118],"models":[28,120],"for":[29,55,82,180,235],"mining":[31,59,76,85],"tasks.":[32],"process":[38],"assigning":[40],"a":[41,45,95,127,232],"particular":[46],"predefined":[47],"category":[48],"based":[49,155],"labelled":[51],"data.":[52],"It":[53],"serves":[54],"several":[56,83,106],"other":[57],"tasks,":[60,86],"such":[61],"as":[62],"focused":[63],"crawling,":[65],"link":[67],"analysis":[68,129],"contextual":[70],"advertising.":[71],"Machine":[72],"learning":[73,147,193],"methods":[77,148,179,248,255],"have":[78],"been":[79],"successfully":[80],"applied":[81],"including":[87],"classification.":[90,183,204,238],"Multiple":[91],"classifier":[92],"systems":[93],"are":[94],"promising":[96,233],"in":[99,201,259],"machine":[100],"learning,":[101],"which":[102,230],"aims":[103],"combine":[105],"classifiers":[107,111,200],"by":[108],"differentiating":[109],"base":[110,159],"and/or":[112],"dataset":[113],"distributions":[114],"so":[115],"that":[116,188,242],"more":[117],"can":[121,194],"be":[122],"built.":[123],"This":[124],"paper":[125],"presents":[126],"comparative":[128],"four":[131,144,157],"different":[132,145,158],"feature":[133,141,189,222,253],"selections":[134],"(correlation,":[135],"consistency,":[136],"information":[137],"gain":[138],"chi-square-based":[140],"selection)":[142],"ensemble":[146,178,192,247],"(Boosting,":[149],"Bagging,":[150],"Dagging":[151],"Random":[153,245],"Subspace)":[154],"learners":[160],"(naive":[161],"Bayes,":[162],"K-nearest":[163],"neighbour":[164],"algorithm,":[165],"C4.5":[166],"algorithm":[167],"FURIA":[169],"algorithm).":[170],"article":[172],"examines":[173],"predictive":[175,197,212],"performance":[176,198,213],"experimental":[185],"results":[186,240,258],"indicate":[187,241],"selection":[190,223,254],"enhance":[195],"For":[205],"DMOZ-50":[207],"dataset,":[208],"highest":[210],"average":[211],"(88.1%)":[214],"obtained":[216],"with":[217,224],"combination":[219],"consistency-based":[221,252],"AdaBoost":[225],"naive":[227],"Bayes":[228],"algorithms,":[229],"result":[234],"Experimental":[239],"Bagging":[243],"Subspace":[246],"correlation-based":[250],"obtain":[256],"better":[257],"terms":[260],"accuracy":[262],"rates.":[263]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":36},{"year":2021,"cited_by_count":35},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":10},{"year":2015,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}