{"id":"https://openalex.org/W2076652827","doi":"https://doi.org/10.1109/fskd.2010.5569792","title":"Measuring similarity of web pages on maximum isomorphic subtree","display_name":"Measuring similarity of web pages on maximum isomorphic subtree","publication_year":2010,"publication_date":"2010-08-01","ids":{"openalex":"https://openalex.org/W2076652827","doi":"https://doi.org/10.1109/fskd.2010.5569792","mag":"2076652827"},"language":"en","primary_location":{"id":"doi:10.1109/fskd.2010.5569792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2010.5569792","pdf_url":null,"source":{"id":"https://openalex.org/S4363608217","display_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","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":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","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/A5101593239","display_name":"Zhenyu Hu","orcid":"https://orcid.org/0000-0003-3799-3299"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhenyu Hu","raw_affiliation_strings":["National Laboratory of Information Science and Technology, Tsinghua University, Beijing, China","National Laboratory of Information Science and Technology, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"National Laboratory of Information Science and Technology, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055546056","display_name":"Fuchun Sun","orcid":"https://orcid.org/0000-0003-3546-6305"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fuchun Sun","raw_affiliation_strings":["National Laboratory of Information Science and Technology, Tsinghua University, Beijing, China","National Laboratory of Information Science and Technology, Tsinghua University, Beijing 100084, China"],"affiliations":[{"raw_affiliation_string":"National Laboratory of Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"National Laboratory of Information Science and Technology, Tsinghua University, Beijing 100084, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101593239"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24212598,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"28","issue":null,"first_page":"2469","last_page":"2473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9954000115394592,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9884999990463257,"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/similarity","display_name":"Similarity (geometry)","score":0.748602569103241},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7054912447929382},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.6707013845443726},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.6604658365249634},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6171497106552124},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5979006886482239},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5580090284347534},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.45470792055130005},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.45088350772857666},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.43647894263267517},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.41863518953323364},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4170720875263214},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32390451431274414},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.29279905557632446},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.2664303779602051},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2626970112323761},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22014689445495605},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17563608288764954},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1316063106060028},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06945481896400452}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.748602569103241},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7054912447929382},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6707013845443726},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.6604658365249634},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6171497106552124},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5979006886482239},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5580090284347534},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45470792055130005},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.45088350772857666},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.43647894263267517},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.41863518953323364},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4170720875263214},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32390451431274414},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.29279905557632446},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2664303779602051},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2626970112323761},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22014689445495605},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17563608288764954},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1316063106060028},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06945481896400452},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fskd.2010.5569792","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fskd.2010.5569792","pdf_url":null,"source":{"id":"https://openalex.org/S4363608217","display_name":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","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":"2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery","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":8,"referenced_works":["https://openalex.org/W270849871","https://openalex.org/W1978478796","https://openalex.org/W1995213245","https://openalex.org/W2035902703","https://openalex.org/W2122530852","https://openalex.org/W2351974641","https://openalex.org/W2362391441","https://openalex.org/W2533369982"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2892165056","https://openalex.org/W2373402338","https://openalex.org/W2098964748","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W2998827288","https://openalex.org/W2076910790","https://openalex.org/W2275993472","https://openalex.org/W2155199173"],"abstract_inverted_index":{"This":[0],"paper":[1,55],"studies":[2],"the":[3,26,61,74,85,88,128],"problem":[4],"of":[5,18,21,29,63,91,118],"comparing":[6],"or":[7],"looking":[8,68],"for":[9,69,101],"structured":[10,103,136],"data":[11],"in":[12,33,73],"DOM":[13,31,44],"trees.":[14],"The":[15],"proposed":[16,129],"notion":[17],"structure":[19,27],"descriptor":[20],"ordered":[22],"tree":[23,32,45],"fully":[24],"represents":[25],"information":[28],"a":[30,34,43,106,116],"serialized":[35,75],"style,":[36],"indicating":[37],"an":[38,57],"efficient":[39],"method":[40],"to":[41,59,80,99,133],"convert":[42],"into":[46],"its":[47,109],"node":[48,76],"sequence.":[49],"Based":[50],"on":[51],"this":[52,54],"notion,":[53],"produced":[56],"algorithm":[58,86],"measure":[60],"similarity":[62],"two":[64,82],"web":[65,83,107,121],"pages,":[66,84],"by":[67],"maximum":[70],"isomorphic":[71],"subtrees":[72],"sequences.":[77],"When":[78],"used":[79,98],"compare":[81],"has":[87],"time":[89],"complexity":[90,110],"O(n":[92],"<sup":[93],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[94],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[95],"),":[96],"while":[97],"look":[100],"certain":[102],"object":[104],"from":[105,123],"page,":[108],"reaches":[111],"O(n).":[112],"Experimental":[113],"results":[114],"using":[115],"number":[117],"well":[119],"known":[120],"pages":[122],"diverse":[124],"domains":[125],"show":[126],"that":[127],"technique":[130],"is":[131],"able":[132],"identify":[134],"similar":[135],"objects":[137],"very":[138],"accurately.":[139]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
