{"id":"https://openalex.org/W2063147917","doi":"https://doi.org/10.1145/1083356.1083384","title":"Separating XHTML content from navigation clutter using DOM-structure block analysis","display_name":"Separating XHTML content from navigation clutter using DOM-structure block analysis","publication_year":2005,"publication_date":"2005-09-06","ids":{"openalex":"https://openalex.org/W2063147917","doi":"https://doi.org/10.1145/1083356.1083384","mag":"2063147917"},"language":"en","primary_location":{"id":"doi:10.1145/1083356.1083384","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1083356.1083384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixteenth ACM conference on Hypertext and hypermedia","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":"Constantine Mantratzis","raw_affiliation_strings":["Macquarie University, Australia","Macquarie Univ., Australia#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University, Australia","institution_ids":["https://openalex.org/I99043593"]},{"raw_affiliation_string":"Macquarie Univ., Australia#TAB#","institution_ids":["https://openalex.org/I99043593"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010152619","display_name":"Mehmet A. Orgun","orcid":"https://orcid.org/0000-0002-7873-1562"},"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":"Mehmet Orgun","raw_affiliation_strings":["Macquarie University, Australia","Macquarie Univ., Australia#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University, Australia","institution_ids":["https://openalex.org/I99043593"]},{"raw_affiliation_string":"Macquarie Univ., Australia#TAB#","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":"Steve Cassidy","raw_affiliation_strings":["Macquarie University, Australia","Macquarie Univ., Australia#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Macquarie University, Australia","institution_ids":["https://openalex.org/I99043593"]},{"raw_affiliation_string":"Macquarie Univ., Australia#TAB#","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":0.7503,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.70716582,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"145","last_page":"147"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9857000112533569,"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":0.9751999974250793,"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":0.8372931480407715},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6360571384429932},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.6263167858123779},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.5913079977035522},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5371369123458862},{"id":"https://openalex.org/keywords/xhtml","display_name":"XHTML","score":0.5341305732727051},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.5074159502983093},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.5025022029876709},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.4668605625629425},{"id":"https://openalex.org/keywords/clutter","display_name":"Clutter","score":0.44845056533813477},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4442650079727173},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.44164973497390747},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4324762523174286},{"id":"https://openalex.org/keywords/markup-language","display_name":"Markup language","score":0.39861103892326355},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3971785008907318},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3075519800186157},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.21591880917549133},{"id":"https://openalex.org/keywords/radar","display_name":"Radar","score":0.2013443112373352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8372931480407715},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6360571384429932},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.6263167858123779},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.5913079977035522},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5371369123458862},{"id":"https://openalex.org/C189139006","wikidata":"https://www.wikidata.org/wiki/Q166074","display_name":"XHTML","level":4,"score":0.5341305732727051},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.5074159502983093},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.5025022029876709},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.4668605625629425},{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.44845056533813477},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4442650079727173},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.44164973497390747},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4324762523174286},{"id":"https://openalex.org/C45874996","wikidata":"https://www.wikidata.org/wiki/Q37045","display_name":"Markup language","level":3,"score":0.39861103892326355},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3971785008907318},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3075519800186157},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.21591880917549133},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.2013443112373352},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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:10.1145/1083356.1083384","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1083356.1083384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixteenth ACM conference on Hypertext and hypermedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"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/W2151775549"],"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],"short":[1],"paper":[2],"gives":[3],"an":[4,10],"overview":[5],"of":[6,16,29,55,103],"the":[7,14,70,81,101],"principles":[8],"behind":[9],"algorithm":[11],"that":[12],"separates":[13],"core-content":[15,82],"a":[17,84,105],"web":[18,85,106],"document":[19,86,107],"from":[20,83],"hyperlinked-clutter":[21],"such":[22,117],"as":[23,46,48,95,97,118],"text":[24],"advertisements":[25],"and":[26,120],"long":[27],"links":[28],"syndicated":[30],"references":[31],"to":[32,42,60,79,98,108],"other":[33,37,91],"resources.Its":[34],"advantage":[35],"over":[36],"approaches":[38],"is":[39],"its":[40,109],"ability":[41],"identify":[43],"both":[44],"loosely":[45],"well":[47,96],"tightly":[49],"defined":[50],"\"table-like\"":[51],"or":[52,90],"\"list-like\"":[53],"structures":[54],"hyperlinks":[56],"(from":[57],"nested":[58],"tables":[59],"simple,":[61],"bullet-pointed":[62],"lists)":[63],"by":[64],"operating":[65],"at":[66],"various":[67],"levels":[68],"within":[69],"DOM":[71],"tree.The":[72],"resulting":[73],"data":[74],"can":[75],"then":[76],"be":[77],"used":[78],"extract":[80],"for":[87,112],"semantic":[88],"analysis":[89],"information":[92],"retrieval":[93],"purposes":[94],"aid":[99],"in":[100],"process":[102],"\"clipping\"":[104],"bare":[110],"essentials":[111],"use":[113],"with":[114],"hardware-limited":[115],"devices":[116],"PDAs":[119],"cell":[121],"phones.":[122]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
