{"id":"https://openalex.org/W2142725362","doi":"https://doi.org/10.1109/icsmc.2008.4811496","title":"Basic semantic units based web page content extraction","display_name":"Basic semantic units based web page content extraction","publication_year":2008,"publication_date":"2008-10-01","ids":{"openalex":"https://openalex.org/W2142725362","doi":"https://doi.org/10.1109/icsmc.2008.4811496","mag":"2142725362"},"language":"en","primary_location":{"id":"doi:10.1109/icsmc.2008.4811496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2008.4811496","pdf_url":null,"source":{"id":"https://openalex.org/S4210195764","display_name":"Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics","issn_l":"1062-922X","issn":["1062-922X","2577-1655"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Systems, Man and Cybernetics","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/A5101497158","display_name":"Jingqi Wang","orcid":"https://orcid.org/0000-0001-6244-4932"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingqi Wang","raw_affiliation_strings":["Intelligence Computing Research Center, Harbin Institute of Technology, China","Shenzhen Grad. Sch., Intell. Comput. Res. Center, Harbin Inst. of Technol., Harbin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligence Computing Research Center, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Shenzhen Grad. Sch., Intell. Comput. Res. Center, Harbin Inst. of Technol., Harbin","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101895423","display_name":"Qingcai Chen","orcid":"https://orcid.org/0000-0001-8473-7293"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingcai Chen","raw_affiliation_strings":["Intelligence Computing Research Center, Harbin Institute of Technology, China","Shenzhen Grad. Sch., Intell. Comput. Res. Center, Harbin Inst. of Technol., Harbin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligence Computing Research Center, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Shenzhen Grad. Sch., Intell. Comput. Res. Center, Harbin Inst. of Technol., Harbin","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006957378","display_name":"Xiaolong Wang","orcid":"https://orcid.org/0000-0002-6037-9871"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaolong Wang","raw_affiliation_strings":["Intelligence Computing Research Center, Harbin Institute of Technology, China","Shenzhen Grad. Sch., Intell. Comput. Res. Center, Harbin Inst. of Technol., Harbin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligence Computing Research Center, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Shenzhen Grad. Sch., Intell. Comput. Res. Center, Harbin Inst. of Technol., Harbin","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082797386","display_name":"Hongzhi Guo","orcid":"https://orcid.org/0000-0002-2503-2784"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Guo","raw_affiliation_strings":["Intelligence Computing Research Center, Harbin Institute of Technology, China","Shenzhen Grad. Sch., Intell. Comput. Res. Center, Harbin Inst. of Technol., Harbin"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligence Computing Research Center, Harbin Institute of Technology, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Shenzhen Grad. Sch., Intell. Comput. Res. Center, Harbin Inst. of Technol., Harbin","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I204983213"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"43","issue":null,"first_page":"1489","last_page":"1494"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9434000253677368,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9107000231742859,"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":0.823861300945282},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.7254433035850525},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6582229137420654},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6007152795791626},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5748497843742371},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5488567352294922},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.4940822422504425},{"id":"https://openalex.org/keywords/paragraph","display_name":"Paragraph","score":0.481135755777359},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.4791676104068756},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.45127761363983154},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4461650252342224},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.42161649465560913},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3484400808811188},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3475881516933441},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.19438034296035767},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09225031733512878}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.823861300945282},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.7254433035850525},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6582229137420654},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6007152795791626},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5748497843742371},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5488567352294922},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.4940822422504425},{"id":"https://openalex.org/C2777206241","wikidata":"https://www.wikidata.org/wiki/Q194431","display_name":"Paragraph","level":2,"score":0.481135755777359},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.4791676104068756},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.45127761363983154},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4461650252342224},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.42161649465560913},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3484400808811188},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3475881516933441},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.19438034296035767},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09225031733512878},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icsmc.2008.4811496","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icsmc.2008.4811496","pdf_url":null,"source":{"id":"https://openalex.org/S4210195764","display_name":"Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics","issn_l":"1062-922X","issn":["1062-922X","2577-1655"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Systems, Man and Cybernetics","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":10,"referenced_works":["https://openalex.org/W1566513354","https://openalex.org/W2012575882","https://openalex.org/W2019264297","https://openalex.org/W2034607275","https://openalex.org/W2151265933","https://openalex.org/W2169347997","https://openalex.org/W2382432786","https://openalex.org/W2388011689","https://openalex.org/W4244354591","https://openalex.org/W6710088911"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W2411838016","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W2076910790","https://openalex.org/W2155199173","https://openalex.org/W2275993472","https://openalex.org/W2998827288","https://openalex.org/W1544491176"],"abstract_inverted_index":{"Web":[0,136],"page":[1,65,104,137],"content":[2,27,42,85],"extraction":[3],"can":[4,36],"be":[5],"achieved":[6],"by":[7,133,143],"node-based":[8,23],"and":[9,84,97,145],"segmentation-based":[10,34],"algorithms":[11,56],"respectively":[12],"on":[13,93],"top":[14],"of":[15,55,62],"the":[16,22,33,49,59,63,81,110,115,119,125,139],"document":[17],"object":[18],"model":[19],"(DOM).":[20],"However,":[21],"algorithm":[24],"often":[25],"removes":[26],"embedded":[28],"as":[29],"anchor":[30],"text;":[31],"while":[32,114],"way":[35],"not":[37],"distinguish":[38],"irrelevant":[39],"text":[40,43,130],"from":[41],"when":[44],"they":[45],"are":[46,100,141],"divided":[47],"into":[48],"same":[50],"segment.":[51],"The":[52,106],"two":[53],"kinds":[54],"don't":[57],"keep":[58],"paragraph":[60],"information":[61],"original":[64],"either.":[66],"In":[67],"this":[68],"paper,":[69],"a":[70],"new":[71],"basic":[72],"semantic":[73],"unit":[74],"(BSU)":[75],"with":[76,124],"granularity":[77],"between":[78],"nodes":[79],"in":[80],"DOM":[82],"tree":[83],"block":[86],"is":[87],"defined.":[88],"Two":[89],"different":[90],"methods":[91],"based":[92],"BSU,":[94],"using":[95],"clustering":[96,107],"heuristic":[98,116],"rules":[99,117],"developed":[101],"to":[102],"extract":[103],"content.":[105],"method":[108,127],"gets":[109],"best":[111,120],"precision":[112],"96.88%;":[113],"obtain":[118],"F1-value":[121],"95.28%.":[122],"Compared":[123],"baseline":[126],"which":[128],"uses":[129],"blocks":[131],"segmented":[132],"<table>and":[134],"<div>as":[135],"content,":[138],"F1-values":[140],"enhanced":[142],"8.92%":[144],"9.42%":[146],"respectively.":[147]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}