{"id":"https://openalex.org/W2018685679","doi":"https://doi.org/10.1109/siu.2012.6204476","title":"Web content extraction by using decision tree learning","display_name":"Web content extraction by using decision tree learning","publication_year":2012,"publication_date":"2012-04-01","ids":{"openalex":"https://openalex.org/W2018685679","doi":"https://doi.org/10.1109/siu.2012.6204476","mag":"2018685679"},"language":"en","primary_location":{"id":"doi:10.1109/siu.2012.6204476","doi":"https://doi.org/10.1109/siu.2012.6204476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2012.6204476","pdf_url":null,"source":{"id":"https://openalex.org/S4363607818","display_name":"Signal Processing and Communications Applications Conference (SIU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5078816512","display_name":"Erdin\u00e7 Uzun","orcid":"https://orcid.org/0000-0003-4351-2244","observed_orcids":["https://orcid.org/0000-0003-4351-2244"]},"institutions":[{"id":"https://openalex.org/I125454184","display_name":"Tekirda\u011f Nam\u0131k Kemal University","ror":"https://ror.org/01a0mk874","country_code":"TR","type":"education","lineage":["https://openalex.org/I125454184"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Erdinc Uzun","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Nam\u0131k Kemal \u00dcniversitesi, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Nam\u0131k Kemal \u00dcniversitesi, Turkey","institution_ids":["https://openalex.org/I125454184"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078860359","display_name":"Hayri Volkan Agun","orcid":"https://orcid.org/0000-0002-4253-8920","observed_orcids":["https://orcid.org/0000-0002-4253-8920"]},"institutions":[{"id":"https://openalex.org/I12387023","display_name":"Trakya University","ror":"https://ror.org/00xa0xn82","country_code":"TR","type":"education","lineage":["https://openalex.org/I12387023"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"H. Volkan Agun","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Trakya \u00dcniversitesi, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Trakya \u00dcniversitesi, Turkey","institution_ids":["https://openalex.org/I12387023"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058453383","display_name":"Tar\u0131k Yerlikaya","orcid":"https://orcid.org/0000-0002-9888-0151","observed_orcids":["https://orcid.org/0000-0002-9888-0151"]},"institutions":[{"id":"https://openalex.org/I12387023","display_name":"Trakya University","ror":"https://ror.org/00xa0xn82","country_code":"TR","type":"education","lineage":["https://openalex.org/I12387023"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Tarik Yerlikaya","raw_affiliation_strings":["Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Trakya \u00dcniversitesi, Turkey"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bilgisayar M\u00fchendisli\u011fi B\u00f6l\u00fcm\u00fc, Trakya \u00dcniversitesi, Turkey","institution_ids":["https://openalex.org/I12387023"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2515,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.50253469,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.0,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0,"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/web-content-extraction","display_name":"web content extraction","score":0.9729999899864197},{"id":"https://openalex.org/keywords/decision-tree-induction","display_name":"decision tree induction","score":0.7089999914169312},{"id":"https://openalex.org/keywords/html-tags","display_name":"HTML tags","score":0.6869999766349792},{"id":"https://openalex.org/keywords/main-content-extraction","display_name":"main content extraction","score":0.8370000123977661},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.5}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8076313734054565},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6144780516624451},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5620734691619873},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5179771184921265},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.49918603897094727},{"id":"https://openalex.org/C4725764","wikidata":"https://www.wikidata.org/wiki/Q844704","display_name":"Extraction (chemistry)","level":2,"score":0.48880383372306824},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.46398070454597473},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4517395794391632},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.42796558141708374},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42557913064956665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4027666747570038},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36185792088508606},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21514776349067688},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10049399733543396},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/siu.2012.6204476","doi":"https://doi.org/10.1109/siu.2012.6204476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu.2012.6204476","pdf_url":null,"source":{"id":"https://openalex.org/S4363607818","display_name":"Signal Processing and Communications Applications Conference (SIU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 20th Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"},{"id":"pmh:oai:acikerisim.trakya.edu.tr:20.500.14551/16328","doi":null,"is_oa":false,"landing_page_url":"https://doi.org/10.1109/SIU.2012.6204476","pdf_url":null,"source":{"id":"https://openalex.org/S4306401406","display_name":"Trakya University's Institutional Open Access System (Trakya University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I12387023","host_organization_name":"Trakya University","host_organization_lineage":["https://openalex.org/I12387023"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Object"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W173956503","https://openalex.org/W1594031697","https://openalex.org/W1988121588","https://openalex.org/W2019264297","https://openalex.org/W2089960290","https://openalex.org/W2094710333","https://openalex.org/W2100406636","https://openalex.org/W2101909884","https://openalex.org/W2113839604","https://openalex.org/W2120101509","https://openalex.org/W2125055259","https://openalex.org/W2133990480","https://openalex.org/W2167859982","https://openalex.org/W4234752074","https://openalex.org/W4244354591"],"related_works":["https://openalex.org/W2898763787","https://openalex.org/W2049488566","https://openalex.org/W2804022826","https://openalex.org/W2280422423","https://openalex.org/W2515878395","https://openalex.org/W1997836898","https://openalex.org/W2385030754","https://openalex.org/W2316898980","https://openalex.org/W2091855574","https://openalex.org/W7097575993"],"abstract_inverted_index":{"Via":[0],"information":[1],"extraction":[2,44,99,121,129],"techniques,":[3],"web":[4,38],"pages":[5,39],"are":[6,32],"able":[7],"to":[8,69],"generate":[9],"datasets":[10],"for":[11,97,127],"various":[12],"studies":[13],"such":[14],"as":[15],"natural":[16],"language":[17],"processing,":[18],"and":[19,30,43,74,84,107,120],"data":[20],"mining.":[21],"However,":[22],"nowadays":[23],"the":[24,71,94,98,101,123,128,131],"uninformative":[25,41,72,118],"sections":[26,73,119],"like":[27],"advertisement,":[28],"menus,":[29],"links":[31],"in":[33,78,116],"increase.":[34],"The":[35,110],"cleaning":[36,117],"of":[37,45,100,122,130],"from":[40,91],"sections,":[42],"informative":[46,76,124],"content":[47,77,103],"has":[48],"become":[49],"an":[50,58],"important":[51],"issue.":[52],"In":[53],"this":[54,88],"study,":[55],"we":[56],"present":[57],"decision":[59],"tree":[60],"learning":[61,95],"approach":[62],"over":[63],"DOM":[64],"based":[65],"features":[66],"which":[67],"aims":[68],"clean":[70],"extract":[75],"three":[79],"classes:":[80],"title,":[81],"main":[82,102,132],"content,":[83],"additional":[85],"information.":[86],"Through":[87],"approach,":[89],"differently":[90],"previous":[92],"studies,":[93],"model":[96],"constructed":[104],"on":[105],"DIV":[106],"TD":[108],"tags.":[109],"proposed":[111],"method":[112],"achieved":[113],"95.58%":[114],"accuracy":[115],"content.":[125],"Especially":[126],"block,":[133],"0.96":[134],"f-measure":[135],"is":[136],"obtained.":[137]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}