{"id":"https://openalex.org/W2051097555","doi":"https://doi.org/10.1145/1242572.1242622","title":"Robust web page segmentation for mobile terminal using content-distances and page layout information","display_name":"Robust web page segmentation for mobile terminal using content-distances and page layout information","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2051097555","doi":"https://doi.org/10.1145/1242572.1242622","mag":"2051097555"},"language":"en","primary_location":{"id":"doi:10.1145/1242572.1242622","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","raw_type":"proceedings-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/A5069839620","display_name":"Gen Hattori","orcid":"https://orcid.org/0000-0001-5636-1065"},"institutions":[{"id":"https://openalex.org/I4210164495","display_name":"KDDI Research (Japan)","ror":"https://ror.org/05qsqt662","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210164495"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Gen Hattori","raw_affiliation_strings":["KDDI R&amp;D Laboratories Inc., Fujimino-shi Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"KDDI R&amp;D Laboratories Inc., Fujimino-shi Saitama, Japan","institution_ids":["https://openalex.org/I4210164495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053493294","display_name":"Keiichiro Hoashi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164495","display_name":"KDDI Research (Japan)","ror":"https://ror.org/05qsqt662","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210164495"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keiichiro Hoashi","raw_affiliation_strings":["KDDI R&amp;D Laboratories Inc., Fujimino-shi Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"KDDI R&amp;D Laboratories Inc., Fujimino-shi Saitama, Japan","institution_ids":["https://openalex.org/I4210164495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071118987","display_name":"Kazunori Matsumoto","orcid":"https://orcid.org/0000-0002-5753-0104"},"institutions":[{"id":"https://openalex.org/I4210164495","display_name":"KDDI Research (Japan)","ror":"https://ror.org/05qsqt662","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210164495"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazunori Matsumoto","raw_affiliation_strings":["KDDI R&amp;D Laboratories Inc., Fujimino-shi Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"KDDI R&amp;D Laboratories Inc., Fujimino-shi Saitama, Japan","institution_ids":["https://openalex.org/I4210164495"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047792532","display_name":"Fumiaki Sugaya","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164495","display_name":"KDDI Research (Japan)","ror":"https://ror.org/05qsqt662","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210164495"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Fumiaki Sugaya","raw_affiliation_strings":["KDDI R&amp;D Laboratories Inc., Fujimino-shi Saitama, Japan"],"affiliations":[{"raw_affiliation_string":"KDDI R&amp;D Laboratories Inc., Fujimino-shi Saitama, Japan","institution_ids":["https://openalex.org/I4210164495"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069839620"],"corresponding_institution_ids":["https://openalex.org/I4210164495"],"apc_list":null,"apc_paid":null,"fwci":11.8681,"has_fulltext":false,"cited_by_count":73,"citation_normalized_percentile":{"value":0.98163524,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"361","last_page":"370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.9638000130653381,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9632999897003174,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.8703697919845581},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8270934820175171},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.7596129179000854},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.6721469759941101},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6033894419670105},{"id":"https://openalex.org/keywords/page-view","display_name":"Page view","score":0.552882730960846},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5452878475189209},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4460153877735138}],"concepts":[{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8703697919845581},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8270934820175171},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.7596129179000854},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.6721469759941101},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6033894419670105},{"id":"https://openalex.org/C103645729","wikidata":"https://www.wikidata.org/wiki/Q911187","display_name":"Page view","level":5,"score":0.552882730960846},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5452878475189209},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4460153877735138}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1242572.1242622","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W40887623","https://openalex.org/W65299677","https://openalex.org/W1557790983","https://openalex.org/W2011506639","https://openalex.org/W2026642282","https://openalex.org/W2041449954","https://openalex.org/W2054099078","https://openalex.org/W2084036689","https://openalex.org/W2096758445","https://openalex.org/W2098995791","https://openalex.org/W2102508811","https://openalex.org/W2137765357","https://openalex.org/W2147428516","https://openalex.org/W2154484245","https://openalex.org/W2169337167"],"related_works":["https://openalex.org/W2055154498","https://openalex.org/W2404573736","https://openalex.org/W2045069236","https://openalex.org/W2051097555","https://openalex.org/W4230700435","https://openalex.org/W2389737178","https://openalex.org/W2167278502","https://openalex.org/W2087758976","https://openalex.org/W2001684880","https://openalex.org/W2074126298"],"abstract_inverted_index":{"The":[0],"demand":[1],"of":[2,19,76,122,141,159,202,225],"browsing":[3,28],"information":[4,41],"from":[5,29,42],"general":[6],"Web":[7,20,51,66,99,126,161,174,192,203,214,243],"pages":[8,21,52,175,215],"using":[9],"a":[10,46,82,96,132,160,168,187],"mobile":[11,35,54,86,230],"phone":[12,36,55,87,231],"is":[13,32,57,62],"increasing.":[14],"However,":[15,128],"since":[16],"the":[17,23,43,65,74,77,105,112,118,135,139,149,156,179,183,200,209,229],"majority":[18],"on":[22,69,111,138,155,177,228],"Internet":[24],"are":[25],"optimized":[26],"for":[27,34,53,85],"PCs,":[30],"it":[31],"difficult":[33],"users":[37,56],"to":[38,48,63,80,148,198,241],"obtain":[39],"sufficient":[40],"Web.":[44],"Therefore,":[45],"method":[47,171,211,235],"reconstruct":[49],"PC-optimized":[50],"essential.":[58],"An":[59],"example":[60],"approach":[61,189],"segment":[64,213],"page":[67,83,100,193,204],"based":[68,110,137,176],"its":[70],"structure,":[71],"and":[72,120,186,223],"utilize":[73],"hierarchy":[75],"content":[78,108,153],"element":[79],"regenerate":[81],"suitable":[84],"browsing.":[88],"In":[89,163],"our":[90,226,234],"previous":[91,184],"work,":[92],"we":[93,166],"have":[94],"examined":[95],"robust":[97],"automatic":[98],"segmentation":[101,170,205],"scheme":[102,130],"which":[103,172,190],"uses":[104],"distance":[106,151],"between":[107,152],"elements":[109,154],"relative":[113],"HTML":[114,123,142],"tag":[115],"hierarchy,":[116],"i.e.,":[117],"number":[119],"depth":[121],"tags":[124,143],"in":[125],"pages.":[127],"this":[129,164],"has":[131],"problem":[133],"that":[134,208,233],"content-distance":[136,180],"order":[140],"does":[144],"not":[145],"always":[146],"correspond":[147],"intuitional":[150],"actual":[157],"layout":[158,194],"page.":[162],"paper,":[165],"propose":[167],"hybrid":[169],"segments":[173],"both":[178],"calculated":[181],"by":[182],"scheme,":[185],"novel":[188],"utilizes":[191],"information.":[195],"Experiments":[196],"conducted":[197],"evaluate":[199],"accuracy":[201],"results":[206],"prove":[207,232],"proposed":[210],"can":[212,236],"more":[216],"accurately":[217],"than":[218],"conventional":[219],"methods.":[220],"Furthermore,":[221],"implementation":[222],"evaluation":[224],"system":[227],"realize":[237],"superior":[238],"usability":[239],"compared":[240],"commercial":[242],"browsers.":[244]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":13},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":11}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
