{"id":"https://openalex.org/W2119577990","doi":"https://doi.org/10.1145/1281192.1281286","title":"Mining templates from search result records of search engines","display_name":"Mining templates from search result records of search engines","publication_year":2007,"publication_date":"2007-08-12","ids":{"openalex":"https://openalex.org/W2119577990","doi":"https://doi.org/10.1145/1281192.1281286","mag":"2119577990"},"language":"en","primary_location":{"id":"doi:10.1145/1281192.1281286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5062551149","display_name":"Hongkun Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongkun Zhao","raw_affiliation_strings":["State University of New York at Binghamton","State University of New York at Binghamton,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Binghamton","institution_ids":["https://openalex.org/I123946342"]},{"raw_affiliation_string":"State University of New York at Binghamton,","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101960531","display_name":"Weiyi Meng","orcid":"https://orcid.org/0000-0002-7246-2058"},"institutions":[{"id":"https://openalex.org/I123946342","display_name":"Binghamton University","ror":"https://ror.org/008rmbt77","country_code":"US","type":"education","lineage":["https://openalex.org/I123946342"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiyi Meng","raw_affiliation_strings":["State University of New York at Binghamton","State University of New York at Binghamton,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State University of New York at Binghamton","institution_ids":["https://openalex.org/I123946342"]},{"raw_affiliation_string":"State University of New York at Binghamton,","institution_ids":["https://openalex.org/I123946342"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109181755","display_name":"Clement Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clement Yu","raw_affiliation_strings":["University of Illinois at Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois at Chicago","institution_ids":["https://openalex.org/I39422238"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.581,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.9581749,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"884","last_page":"893"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9771999716758728,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9648000001907349,"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":0.7864056825637817},{"id":"https://openalex.org/keywords/metasearch-engine","display_name":"Metasearch engine","score":0.769766628742218},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7226467132568359},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.7126660943031311},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.6834351420402527},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.6050928235054016},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.5862878561019897},{"id":"https://openalex.org/keywords/search-analytics","display_name":"Search analytics","score":0.4812464416027069},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.472406804561615},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4435039162635803},{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.4342881441116333},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.30465269088745117},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.28924936056137085}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864056825637817},{"id":"https://openalex.org/C173979980","wikidata":"https://www.wikidata.org/wiki/Q114106","display_name":"Metasearch engine","level":4,"score":0.769766628742218},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7226467132568359},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.7126660943031311},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.6834351420402527},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.6050928235054016},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.5862878561019897},{"id":"https://openalex.org/C14838553","wikidata":"https://www.wikidata.org/wiki/Q7441639","display_name":"Search analytics","level":4,"score":0.4812464416027069},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.472406804561615},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4435039162635803},{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.4342881441116333},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30465269088745117},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.28924936056137085},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1281192.1281286","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281286","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1492472380","https://openalex.org/W1519606823","https://openalex.org/W1553019137","https://openalex.org/W1569691642","https://openalex.org/W1927338256","https://openalex.org/W1973483159","https://openalex.org/W2005646337","https://openalex.org/W2015551056","https://openalex.org/W2027864253","https://openalex.org/W2065568440","https://openalex.org/W2069388662","https://openalex.org/W2102694093","https://openalex.org/W2104086170","https://openalex.org/W2128341918","https://openalex.org/W2128836931","https://openalex.org/W2133669904","https://openalex.org/W2134150392","https://openalex.org/W2138405339","https://openalex.org/W2140327372","https://openalex.org/W2143079043","https://openalex.org/W2143309843","https://openalex.org/W2148210463","https://openalex.org/W2150721933","https://openalex.org/W2152986551","https://openalex.org/W2153072229","https://openalex.org/W2160196229","https://openalex.org/W2166407869","https://openalex.org/W2170188121","https://openalex.org/W2170626955","https://openalex.org/W3015882749","https://openalex.org/W4233527139","https://openalex.org/W4285719527","https://openalex.org/W6681973738","https://openalex.org/W6685116542"],"related_works":["https://openalex.org/W2223855511","https://openalex.org/W2185312392","https://openalex.org/W2419328283","https://openalex.org/W2187685684","https://openalex.org/W2132107051","https://openalex.org/W2170926227","https://openalex.org/W2964491004","https://openalex.org/W2245244370","https://openalex.org/W2106235201","https://openalex.org/W2086329819"],"abstract_inverted_index":{"Metasearch":[0],"engine,":[1],"Comparison-shopping":[2],"and":[3,51,72,103,108,119],"Deep":[4],"Web":[5],"crawling":[6],"applications":[7],"need":[8],"to":[9,24,68,79],"extract":[10,50],"search":[11,20,28,34,87,91,124],"result":[12,16,29,92,125],"records":[13,30],"enwrapped":[14],"in":[15,22],"pages":[17],"returned":[18],"from":[19,31],"engines":[21],"response":[23],"user":[25],"queries.":[26],"The":[27],"a":[32,41,65,74],"given":[33],"engine":[35,88],"are":[36],"usually":[37],"formatted":[38],"based":[39],"on":[40],"template.":[42],"Precisely":[43],"identifying":[44],"this":[45,61,132],"template":[46,71,84,99,104],"can":[47,96],"greatly":[48],"help":[49],"annotate":[52],"the":[53,82,113,116,120],"data":[54,121],"units":[55],"within":[56],"each":[57],"record":[58,70,83],"correctly.":[59],"In":[60],"paper,":[62],"we":[63],"propose":[64],"graph":[66],"model":[67],"represent":[69],"develop":[73],"domain":[75],"independent":[76],"statistical":[77],"method":[78],"automatically":[80],"mine":[81],"for":[85],"any":[86],"using":[89],"sample":[90],"records.":[93,126],"Our":[94,127],"approach":[95,133],"identify":[97],"both":[98],"tags":[100],"(HTML":[101],"tags)":[102],"texts":[105],"(non-tag":[106],"texts),":[107],"it":[109],"also":[110],"explicitly":[111],"addresses":[112],"mismatches":[114],"between":[115],"tag":[117],"structures":[118,122],"of":[123],"experimental":[128],"results":[129],"indicate":[130],"that":[131],"is":[134],"very":[135],"effective.":[136]},"counts_by_year":[{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}