{"id":"https://openalex.org/W2441800827","doi":"https://doi.org/10.1109/tfuzz.2016.2586971","title":"Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation","display_name":"Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation","publication_year":2016,"publication_date":"2016-07-07","ids":{"openalex":"https://openalex.org/W2441800827","doi":"https://doi.org/10.1109/tfuzz.2016.2586971","mag":"2441800827"},"language":"en","primary_location":{"id":"doi:10.1109/tfuzz.2016.2586971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tfuzz.2016.2586971","pdf_url":null,"source":{"id":"https://openalex.org/S134177497","display_name":"IEEE Transactions on Fuzzy Systems","issn_l":"1063-6706","issn":["1063-6706","1941-0034"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Fuzzy Systems","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1606.04429","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053443820","display_name":"Alberto P\u00e9rez Garc\u00eda-Plaza","orcid":"https://orcid.org/0000-0002-2710-9319"},"institutions":[{"id":"https://openalex.org/I178450904","display_name":"Universidad Nacional de Educaci\u00f3n a Distancia","ror":"https://ror.org/02msb5n36","country_code":"ES","type":"education","lineage":["https://openalex.org/I178450904"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Alberto P. Garcia-Plaza","raw_affiliation_strings":["NLP&IR Group, National University of Distance Education, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"NLP&IR Group, National University of Distance Education, Madrid, Spain","institution_ids":["https://openalex.org/I178450904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042675695","display_name":"V\u00edctor Fresno","orcid":"https://orcid.org/0000-0003-4270-2628"},"institutions":[{"id":"https://openalex.org/I178450904","display_name":"Universidad Nacional de Educaci\u00f3n a Distancia","ror":"https://ror.org/02msb5n36","country_code":"ES","type":"education","lineage":["https://openalex.org/I178450904"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Victor Fresno","raw_affiliation_strings":["NLP&IR Group, National University of Distance Education, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"NLP&IR Group, National University of Distance Education, Madrid, Spain","institution_ids":["https://openalex.org/I178450904"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080577159","display_name":"Raquel Mart\u00ednez\u2010Espa\u00f1a","orcid":"https://orcid.org/0000-0002-6750-2203"},"institutions":[{"id":"https://openalex.org/I178450904","display_name":"Universidad Nacional de Educaci\u00f3n a Distancia","ror":"https://ror.org/02msb5n36","country_code":"ES","type":"education","lineage":["https://openalex.org/I178450904"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Raquel Martinez Unanue","raw_affiliation_strings":["NLP&IR Group, National University of Distance Education, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"NLP&IR Group, National University of Distance Education, Madrid, Spain","institution_ids":["https://openalex.org/I178450904"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071220716","display_name":"Arkaitz Zubiaga","orcid":"https://orcid.org/0000-0003-4583-3623"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arkaitz Zubiaga","raw_affiliation_strings":["Department of Computer Science, University of Warwick, Coventry, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Warwick, Coventry, U.K","institution_ids":["https://openalex.org/I39555362"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5053443820"],"corresponding_institution_ids":["https://openalex.org/I178450904"],"apc_list":null,"apc_paid":null,"fwci":0.6906,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.79168722,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"25","issue":"4","first_page":"919","last_page":"933"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9986000061035156,"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":0.9876999855041504,"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":0.8272002339363098},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.7265836000442505},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.696088433265686},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6724367141723633},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.603122889995575},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5258874297142029},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.4942457973957062},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4550604820251465},{"id":"https://openalex.org/keywords/fuzzy-logic","display_name":"Fuzzy logic","score":0.45280978083610535},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.443254679441452},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4368320107460022},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3510322868824005},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3338923156261444},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.2913089990615845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26863983273506165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8272002339363098},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.7265836000442505},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.696088433265686},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6724367141723633},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.603122889995575},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5258874297142029},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.4942457973957062},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4550604820251465},{"id":"https://openalex.org/C58166","wikidata":"https://www.wikidata.org/wiki/Q224821","display_name":"Fuzzy logic","level":2,"score":0.45280978083610535},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.443254679441452},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4368320107460022},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3510322868824005},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3338923156261444},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.2913089990615845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26863983273506165},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tfuzz.2016.2586971","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tfuzz.2016.2586971","pdf_url":null,"source":{"id":"https://openalex.org/S134177497","display_name":"IEEE Transactions on Fuzzy Systems","issn_l":"1063-6706","issn":["1063-6706","1941-0034"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Fuzzy Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1606.04429","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.04429","pdf_url":"https://arxiv.org/pdf/1606.04429","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2441800827","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1606.04429","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/56426","is_oa":false,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/56426","pdf_url":null,"source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"doi:10.48550/arxiv.1606.04429","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1606.04429","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1606.04429","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1606.04429","pdf_url":"https://arxiv.org/pdf/1606.04429","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3123930367","display_name":null,"funder_award_id":"TIN2013-46616-C2-2-R","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W63186855","https://openalex.org/W635933821","https://openalex.org/W781628010","https://openalex.org/W966586055","https://openalex.org/W1535872236","https://openalex.org/W1563243329","https://openalex.org/W1603900533","https://openalex.org/W1606832437","https://openalex.org/W1970544520","https://openalex.org/W1979346351","https://openalex.org/W2006285409","https://openalex.org/W2007926292","https://openalex.org/W2008525336","https://openalex.org/W2026635729","https://openalex.org/W2032304665","https://openalex.org/W2033709196","https://openalex.org/W2037655662","https://openalex.org/W2052621018","https://openalex.org/W2055347269","https://openalex.org/W2059586463","https://openalex.org/W2066915770","https://openalex.org/W2079656678","https://openalex.org/W2083215836","https://openalex.org/W2086528962","https://openalex.org/W2091808810","https://openalex.org/W2098977784","https://openalex.org/W2113072182","https://openalex.org/W2128873747","https://openalex.org/W2132916655","https://openalex.org/W2137570937","https://openalex.org/W2139596625","https://openalex.org/W2158997610","https://openalex.org/W2166601255","https://openalex.org/W2169899598","https://openalex.org/W2220943046","https://openalex.org/W4247444580","https://openalex.org/W4301056670","https://openalex.org/W6604622266","https://openalex.org/W6681822384","https://openalex.org/W6691543865"],"related_works":["https://openalex.org/W1607944674","https://openalex.org/W2015415022","https://openalex.org/W1590167321","https://openalex.org/W2007571138","https://openalex.org/W2951472304","https://openalex.org/W1997909597","https://openalex.org/W2167138081","https://openalex.org/W2017416982","https://openalex.org/W201536428","https://openalex.org/W2744245063","https://openalex.org/W2334294783","https://openalex.org/W2282541595","https://openalex.org/W2132267522","https://openalex.org/W2527445284","https://openalex.org/W1558521370","https://openalex.org/W1985159774","https://openalex.org/W2243769841","https://openalex.org/W1594835650","https://openalex.org/W2413309991","https://openalex.org/W2147057843"],"abstract_inverted_index":{"The":[0,115],"selection":[1],"of":[2,15,41,51,81,103,117,122,131,154,170,179,192],"a":[3,9,16,28,72,97,132,152,167,180],"suitable":[4],"document":[5,17,29,36,86],"representation":[6,99],"approach":[7,76],"plays":[8],"crucial":[10],"role":[11],"in":[12,35],"the":[13,39,44,49,52,79,82,94,111,127,140,158,177],"performance":[14],"clustering":[18,183],"task.":[19,184],"Being":[20],"able":[21],"to":[22,32,63,109,125,156,197],"pick":[23],"out":[24],"representative":[25,65,113],"words":[26],"within":[27,176],"can":[30,59,100,195],"lead":[31],"substantial":[33],"improvements":[34],"clustering.":[37,87],"In":[38,67],"case":[40],"web":[42,118,133,181],"documents,":[43],"HTML":[45,83,123],"markup":[46],"that":[47,58,77,96,138,173],"defines":[48],"layout":[50],"content":[53],"provides":[54],"additional":[55],"structural":[56],"information":[57,159],"be":[60],"further":[61],"exploited":[62],"identify":[64],"words.":[66,114],"this":[68],"paper,":[69],"we":[70,174],"introduce":[71,166],"fuzzy":[73,168,190,211],"term":[74],"weighing":[75],"makes":[78],"most":[80,112,128],"structure":[84],"for":[85],"We":[88,150],"set":[89,153],"forth":[90],"and":[91,165,215],"build":[92],"on":[93],"hypothesis":[95],"good":[98,205],"take":[101],"advantage":[102],"how":[104],"humans":[105],"skim":[106],"through":[107,135],"documents":[108],"extract":[110],"authors":[116],"pages":[119],"make":[120],"use":[121],"tags":[124],"convey":[126],"important":[129],"message":[130],"page":[134,136,145,163,182],"elements":[137],"attract":[139],"readers'":[141],"attention,":[142],"such":[143],"as":[144],"titles":[146],"or":[147],"emphasized":[148],"elements.":[149],"define":[151],"criteria":[155,172,193],"exploit":[157],"provided":[160],"by":[161],"these":[162,171],"elements,":[164],"combination":[169,191],"evaluate":[175],"context":[178],"Our":[185],"proposed":[186],"approach,":[187],"called":[188],"abstract":[189],"(AFCC),":[194],"adapt":[196],"datasets":[198],"whose":[199],"features":[200],"are":[201],"distributed":[202],"differently,":[203],"achieving":[204],"results":[206],"compared":[207],"with":[208],"other":[209],"similar":[210],"logic":[212],"based":[213],"approaches":[214],"TF-IDF":[216],"across":[217],"different":[218],"datasets.":[219]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-16T15:07:20.185449","created_date":"2025-10-10T00:00:00"}