{"id":"https://openalex.org/W2745263186","doi":"https://doi.org/10.1145/3106426.3106437","title":"Navigation objects extraction for better content structure understanding","display_name":"Navigation objects extraction for better content structure understanding","publication_year":2017,"publication_date":"2017-08-10","ids":{"openalex":"https://openalex.org/W2745263186","doi":"https://doi.org/10.1145/3106426.3106437","mag":"2745263186"},"language":"en","primary_location":{"id":"doi:10.1145/3106426.3106437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3106426.3106437","pdf_url":null,"source":{"id":"https://openalex.org/S4306524158","display_name":"Proceedings of the International Conference on Web Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Proceedings of the International Conference on Web Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1708.07940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Kui Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Kui Zhao","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bangpeng Li","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bangpeng Li","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zilun Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zilun Peng","raw_affiliation_strings":["University of British Columbia, Vancouver, Canada"],"affiliations":[{"raw_affiliation_string":"University of British Columbia, Vancouver, Canada","institution_ids":["https://openalex.org/I141945490"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiajun Bu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Bu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":null,"display_name":"Can Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Can Wang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.3604,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58156028,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"629","last_page":"636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9818000197410583,"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":0.9818000197410583,"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/T13976","display_name":"Web visibility and informetrics","score":0.0019000000320374966,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0017000000225380063,"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-page","display_name":"Web page","score":0.8091999888420105},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.6762999892234802},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4462999999523163},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.4456999897956848},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3815000057220459},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.3801000118255615},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3799000084400177},{"id":"https://openalex.org/keywords/dynamic-web-page","display_name":"Dynamic web page","score":0.365200012922287},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3625999987125397}],"concepts":[{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8091999888420105},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7117000222206116},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.6762999892234802},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6087999939918518},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.44679999351501465},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4462999999523163},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.4456999897956848},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3799000084400177},{"id":"https://openalex.org/C100158260","wikidata":"https://www.wikidata.org/wiki/Q1650567","display_name":"Dynamic web page","level":3,"score":0.365200012922287},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3603000044822693},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.3555000126361847},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.3222000002861023},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.3215999901294708},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.31709998846054077},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.303600013256073},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C24733836","wikidata":"https://www.wikidata.org/wiki/Q649186","display_name":"Web mapping","level":4,"score":0.29679998755455017},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.2605000138282776},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3106426.3106437","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3106426.3106437","pdf_url":null,"source":{"id":"https://openalex.org/S4306524158","display_name":"Proceedings of the International Conference on Web Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"Proceedings of the International Conference on Web Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1708.07940","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.07940","pdf_url":"https://arxiv.org/pdf/1708.07940","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1708.07940","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1708.07940","pdf_url":"https://arxiv.org/pdf/1708.07940","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":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1551178608","https://openalex.org/W1565160597","https://openalex.org/W1659541576","https://openalex.org/W1667863317","https://openalex.org/W1980150549","https://openalex.org/W1989338554","https://openalex.org/W2019264297","https://openalex.org/W2019577381","https://openalex.org/W2033403400","https://openalex.org/W2040075907","https://openalex.org/W2051141368","https://openalex.org/W2057017396","https://openalex.org/W2086017131","https://openalex.org/W2109760176","https://openalex.org/W2126326837","https://openalex.org/W2140208587","https://openalex.org/W2158051716","https://openalex.org/W2162833336","https://openalex.org/W2166007234","https://openalex.org/W2175110005","https://openalex.org/W2201534957","https://openalex.org/W2400661088","https://openalex.org/W2997591727","https://openalex.org/W4235169531"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"works":[1],"for":[2,92],"extracting":[3],"navigation":[4,10,93,106,115,119,154],"objects":[5,94,120,155],"from":[6,156,179],"webpages":[7,178],"focus":[8],"on":[9,173],"menus,":[11,107],"so":[12],"as":[13,27,52,167],"to":[14,62],"reveal":[15],"the":[16,20,35,38,63,66,76,104,110,118,141,145,148,160,185],"information":[17],"architecture":[18],"of":[19,37,65,69,139,144,187],"site.":[21],"However,":[22],"web":[23,43,70,80],"2.0":[24,71,81],"sites":[25],"such":[26,51,166],"social":[28],"networks,":[29],"e-commerce":[30],"portals":[31],"etc.":[32,171],"are":[33,60],"making":[34],"understanding":[36,64],"content":[39,77],"structure":[40,78,143],"in":[41,57,79,83,95,121,126],"a":[42,58,88,96,122],"site":[44],"increasingly":[45],"difficult.":[46],"Dynamic":[47],"and":[48,112,147,182],"personalized":[49,113],"elements":[50],"top":[53],"stories,":[54],"recommended":[55],"list":[56],"webpage":[59,123],"vital":[61],"dynamic":[67,111],"nature":[68],"sites.":[72],"To":[73],"better":[74],"understand":[75],"sites,":[82],"this":[84],"paper":[85],"we":[86,128,152],"propose":[87],"new":[89],"extraction":[90],"method":[91,99],"webpage.":[97],"Our":[98],"will":[100],"extract":[101],"not":[102],"only":[103],"static":[105],"but":[108],"also":[109],"page-specific":[114],"lists.":[116],"Since":[117],"naturally":[124],"come":[125],"blocks,":[127],"first":[129],"cluster":[130],"hyperlinks":[131],"into":[132],"different":[133],"blocks":[134,158],"by":[135],"exploiting":[136],"spatial":[137],"locations":[138],"hyperlinks,":[140],"hierarchical":[142],"DOM-tree":[146],"hyperlink":[149],"density.":[150],"Then":[151],"identify":[153],"those":[157],"using":[159],"SVM":[161],"classifier":[162],"with":[163,177],"novel":[164],"features":[165],"anchor":[168],"text":[169],"lengths":[170],"Experiments":[172],"real-world":[174],"data":[175],"sets":[176],"various":[180],"domains":[181],"styles":[183],"verified":[184],"effectiveness":[186],"our":[188],"method.":[189]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2017-08-17T00:00:00"}
