{"id":"https://openalex.org/W1979468824","doi":"https://doi.org/10.1109/icmew.2013.6618450","title":"Extracting the semantic content of web pages via repeated structures","display_name":"Extracting the semantic content of web pages via repeated structures","publication_year":2013,"publication_date":"2013-07-01","ids":{"openalex":"https://openalex.org/W1979468824","doi":"https://doi.org/10.1109/icmew.2013.6618450","mag":"1979468824"},"language":"en","primary_location":{"id":"doi:10.1109/icmew.2013.6618450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew.2013.6618450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","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/A5103675907","display_name":"Zheng He","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheng He","raw_affiliation_strings":["East China Normal University, Shanghai, China","East China Normal University, SHANGHAI, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"East China Normal University, SHANGHAI, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043852046","display_name":"Hangzai Luo","orcid":"https://orcid.org/0000-0003-3354-5739"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangzai Luo","raw_affiliation_strings":["Northwest University of China, Xian, China","Northwest University of China, Xian, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Northwest University of China, Xian, China","institution_ids":["https://openalex.org/I37802460"]},{"raw_affiliation_string":"Northwest University of China, Xian, China#TAB#","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100728564","display_name":"Jianping Fan","orcid":"https://orcid.org/0000-0002-4923-0910"},"institutions":[{"id":"https://openalex.org/I37802460","display_name":"Northwest University","ror":"https://ror.org/00z3td547","country_code":"CN","type":"education","lineage":["https://openalex.org/I37802460"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianping Fan","raw_affiliation_strings":["Northwest University of China, Xian, China","Northwest University of China, Xian, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Northwest University of China, Xian, China","institution_ids":["https://openalex.org/I37802460"]},{"raw_affiliation_string":"Northwest University of China, Xian, China#TAB#","institution_ids":["https://openalex.org/I37802460"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075936732","display_name":"Xiao Liu","orcid":"https://orcid.org/0000-0001-8400-5754"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Liu","raw_affiliation_strings":["East China Normal University, Shanghai, China","East China Normal University, SHANGHAI, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]},{"raw_affiliation_string":"East China Normal University, SHANGHAI, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103675907"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15281034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9485999941825867,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9484999775886536,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.840099573135376},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7552744150161743},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.7293210029602051},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6744306087493896},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6082043647766113},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5852930545806885},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.5689582824707031},{"id":"https://openalex.org/keywords/social-semantic-web","display_name":"Social Semantic Web","score":0.5487070083618164},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.5021357536315918},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.15054994821548462},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09552904963493347}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.840099573135376},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7552744150161743},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.7293210029602051},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6744306087493896},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6082043647766113},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5852930545806885},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.5689582824707031},{"id":"https://openalex.org/C534406577","wikidata":"https://www.wikidata.org/wiki/Q7550843","display_name":"Social Semantic Web","level":3,"score":0.5487070083618164},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.5021357536315918},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.15054994821548462},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09552904963493347}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icmew.2013.6618450","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmew.2013.6618450","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)","raw_type":"proceedings-article"},{"id":"pmh:oai:dro.deakin.edu.au:DU:30097655","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401102","display_name":"Own your potential (DEAKIN)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1989338554","https://openalex.org/W2015551056","https://openalex.org/W2019264297","https://openalex.org/W2019577381","https://openalex.org/W2040075907","https://openalex.org/W2049781914","https://openalex.org/W2061189702","https://openalex.org/W2074231493","https://openalex.org/W2083563309","https://openalex.org/W2089741152","https://openalex.org/W2093559286","https://openalex.org/W2102189859","https://openalex.org/W2117694587","https://openalex.org/W2139599797","https://openalex.org/W2143309843","https://openalex.org/W2146001804","https://openalex.org/W2153635508","https://openalex.org/W4232071090","https://openalex.org/W4240344917","https://openalex.org/W4244354591","https://openalex.org/W4250847188","https://openalex.org/W6671567637"],"related_works":["https://openalex.org/W2349698472","https://openalex.org/W2366430559","https://openalex.org/W1585941060","https://openalex.org/W1975429881","https://openalex.org/W1985801232","https://openalex.org/W2355823470","https://openalex.org/W2025728896","https://openalex.org/W1710908466","https://openalex.org/W4211114681","https://openalex.org/W2023110884"],"abstract_inverted_index":{"Web":[0],"pages":[1,84,102,115],"may":[2,21,50],"carry":[3],"semantics":[4,30],"that":[5,24,75],"are":[6,25],"very":[7],"important":[8],"to":[9,16,27,34,64],"the":[10,13,19,28,32,38,58,78,89,96,109,114],"authors":[11,20],"and":[12],"readers.":[14],"Due":[15],"many":[17],"reasons,":[18],"insert":[22],"contents":[23],"irrelevant":[26],"underlying":[29],"of":[31,37,60,88,113],"page":[33,63],"different":[35],"positions":[36],"page,":[39],"such":[40],"as":[41],"advertizements,":[42],"guide":[43],"bars,":[44],"links.":[45],"As":[46],"a":[47,61,73],"result,":[48],"it":[49],"not":[51],"lead":[52],"good":[53],"effect":[54],"by":[55],"using":[56],"all":[57],"data":[59],"web":[62,83,101],"model":[65],"its":[66],"semantics.":[67],"In":[68],"this":[69],"paper,":[70],"we":[71],"propose":[72],"framework":[74],"can":[76],"extract":[77],"real":[79,97,110,117],"semantic":[80,98,111,118],"content":[81,112],"from":[82,116],"via":[85,103],"repeated":[86,104],"structures":[87],"HTML":[90],"data.":[91],"Our":[92],"algorithm":[93],"first":[94],"detect":[95],"blocks":[99],"in":[100],"structure":[105],"segmentation,":[106],"then":[107],"extracts":[108],"blocks.":[119]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
