{"id":"https://openalex.org/W2121840840","doi":"https://doi.org/10.1109/cimca.2005.1631334","title":"DOM-Based XHTML Document Structure Analysis Separating Content from Navigation Elements","display_name":"DOM-Based XHTML Document Structure Analysis Separating Content from Navigation Elements","publication_year":2006,"publication_date":"2006-05-25","ids":{"openalex":"https://openalex.org/W2121840840","doi":"https://doi.org/10.1109/cimca.2005.1631334","mag":"2121840840"},"language":"en","primary_location":{"id":"doi:10.1109/cimca.2005.1631334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cimca.2005.1631334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06)","raw_type":"proceedings-article"},"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/A5030818681","display_name":"Constantine Mantratzis","orcid":null},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"C. Mantratzis","raw_affiliation_strings":["Department of Computing, Macquarie University, Australia","Dept. of Comput., Macquarie Univ., North Ryde, NSW"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Macquarie University, Australia","institution_ids":["https://openalex.org/I99043593"]},{"raw_affiliation_string":"Dept. of Comput., Macquarie Univ., North Ryde, NSW","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034758801","display_name":"Steve Cassidy","orcid":"https://orcid.org/0000-0003-2357-9652"},"institutions":[{"id":"https://openalex.org/I99043593","display_name":"Macquarie University","ror":"https://ror.org/01sf06y89","country_code":"AU","type":"education","lineage":["https://openalex.org/I99043593"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"S. Cassidy","raw_affiliation_strings":["Department of Computing, Macquarie University, Australia","Dept. of Comput., Macquarie Univ., North Ryde, NSW"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computing, Macquarie University, Australia","institution_ids":["https://openalex.org/I99043593"]},{"raw_affiliation_string":"Dept. of Comput., Macquarie Univ., North Ryde, NSW","institution_ids":["https://openalex.org/I99043593"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99043593"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.18295892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"1","issue":null,"first_page":"632","last_page":"637"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9825000166893005,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.833497166633606},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6835601925849915},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.5827250480651855},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.5824511647224426},{"id":"https://openalex.org/keywords/xhtml","display_name":"XHTML","score":0.5766793489456177},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5681977272033691},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.511980414390564},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.49597224593162537},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.47749775648117065},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44058868288993835},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43197518587112427},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.42589202523231506},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.3893020749092102},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2925647497177124},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.24103254079818726}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833497166633606},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6835601925849915},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.5827250480651855},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.5824511647224426},{"id":"https://openalex.org/C189139006","wikidata":"https://www.wikidata.org/wiki/Q166074","display_name":"XHTML","level":4,"score":0.5766793489456177},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5681977272033691},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.511980414390564},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.49597224593162537},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.47749775648117065},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44058868288993835},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43197518587112427},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.42589202523231506},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.3893020749092102},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2925647497177124},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.24103254079818726},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cimca.2005.1631334","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cimca.2005.1631334","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Conference on Computational Intelligence for Modelling, Control and Automation and International Conference on Intelligent Agents, Web Technologies and Internet Commerce (CIMCA-IAWTIC'06)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W116870935","https://openalex.org/W137938104","https://openalex.org/W1479700690","https://openalex.org/W2012575882","https://openalex.org/W2019264297","https://openalex.org/W2026642282","https://openalex.org/W2070030212","https://openalex.org/W2082884138","https://openalex.org/W2151775549","https://openalex.org/W2157316480","https://openalex.org/W2167859982","https://openalex.org/W2169347997","https://openalex.org/W4235963273","https://openalex.org/W4244354591","https://openalex.org/W6604697442","https://openalex.org/W6605572043","https://openalex.org/W6628730262"],"related_works":["https://openalex.org/W4243796650","https://openalex.org/W1563775010","https://openalex.org/W2774879466","https://openalex.org/W1576556689","https://openalex.org/W2744479763","https://openalex.org/W2501516011","https://openalex.org/W2465578401","https://openalex.org/W279807723","https://openalex.org/W627285271","https://openalex.org/W2203416881"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"an":[3],"algorithm":[4],"that":[5],"attempts":[6],"to":[7,21,41,53,71,91,111,121],"distinguish":[8],"core":[9],"content":[10],"from":[11,29],"clutter":[12],"within":[13,80],"a":[14,97,118],"web":[15,43,98,119],"document.":[16],"The":[17,84],"end":[18],"goal":[19],"is":[20,50],"aid":[22,112],"in":[23,113],"the":[24,27,81,94,114],"separation":[25],"of":[26,38,66,96,116],"core-content":[28,95],"hyperlinked-clutter":[30],"such":[31,130],"as":[32,57,59,108,110,131],"text":[33],"advertisements":[34],"and":[35,133],"long":[36],"links":[37],"syndicated":[39],"references":[40],"other":[42,48,104],"documents.":[44],"Its":[45],"advantage":[46],"over":[47],"approaches":[49],"its":[51,122],"ability":[52],"identify":[54],"both":[55],"loosely":[56],"well":[58,109],"tightly":[60],"defined":[61],"\"table-like\"":[62],"or":[63,103],"\"list-like\"":[64],"structures":[65],"hyperlinks":[67],"(from":[68],"nested":[69],"tables":[70],"simple,":[72],"bullet-pointed":[73],"lists)":[74],"by":[75],"operating":[76],"at":[77],"various":[78],"levels":[79],"DOM":[82],"tree.":[83],"resulting":[85],"data":[86],"can":[87],"then":[88],"be":[89],"used":[90],"\"narrow":[92],"down\"":[93],"document":[99,120],"for":[100,125],"semantic":[101],"analysis":[102],"information":[105],"retrieval":[106],"purposes":[107],"process":[115],"\"clipping\"":[117],"bare":[123],"essentials":[124],"use":[126],"with":[127],"hardware-limited":[128],"devices":[129],"PDAs":[132],"cell":[134],"phones.":[135]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
