{"id":"https://openalex.org/W1994809019","doi":"https://doi.org/10.1109/dbta.2010.5659105","title":"Analysis of Duplicated Web Pages Identification Methods in Search Engine","display_name":"Analysis of Duplicated Web Pages Identification Methods in Search Engine","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W1994809019","doi":"https://doi.org/10.1109/dbta.2010.5659105","mag":"1994809019"},"language":"en","primary_location":{"id":"doi:10.1109/dbta.2010.5659105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dbta.2010.5659105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 2nd International Workshop on Database Technology and Applications","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/A5027147194","display_name":"Fei Duan","orcid":"https://orcid.org/0000-0002-7469-7184"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Duan","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","Sch. Of Comput. Sci., Beijing Univ. of Posts & Telecommun., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Sch. Of Comput. Sci., Beijing Univ. of Posts & Telecommun., Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100694669","display_name":"Zheng Yan","orcid":"https://orcid.org/0000-0002-9067-8020"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Zheng","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","Sch. Of Comput. Sci., Beijing Univ. of Posts & Telecommun., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]},{"raw_affiliation_string":"Sch. Of Comput. Sci., Beijing Univ. of Posts & Telecommun., Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9995999932289124,"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":0.9995999932289124,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9692000150680542,"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/T11719","display_name":"Data Quality and Management","score":0.9449999928474426,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7758500576019287},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.7627139687538147},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6888673305511475},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6349494457244873},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.6153483390808105},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.5931189060211182},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5637760162353516},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5504820346832275},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5074071288108826},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5014021396636963},{"id":"https://openalex.org/keywords/metasearch-engine","display_name":"Metasearch engine","score":0.49803900718688965},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4719858765602112},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.4537927210330963},{"id":"https://openalex.org/keywords/search-analytics","display_name":"Search analytics","score":0.42289119958877563},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.36046069860458374},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.25708746910095215},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.05827173590660095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7758500576019287},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.7627139687538147},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6888673305511475},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6349494457244873},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.6153483390808105},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.5931189060211182},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5637760162353516},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5504820346832275},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5074071288108826},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5014021396636963},{"id":"https://openalex.org/C173979980","wikidata":"https://www.wikidata.org/wiki/Q114106","display_name":"Metasearch engine","level":4,"score":0.49803900718688965},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4719858765602112},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.4537927210330963},{"id":"https://openalex.org/C14838553","wikidata":"https://www.wikidata.org/wiki/Q7441639","display_name":"Search analytics","level":4,"score":0.42289119958877563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36046069860458374},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.25708746910095215},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.05827173590660095},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/dbta.2010.5659105","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dbta.2010.5659105","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 2nd International Workshop on Database Technology and Applications","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":14,"referenced_works":["https://openalex.org/W1596691921","https://openalex.org/W1598064945","https://openalex.org/W1855535104","https://openalex.org/W1968197683","https://openalex.org/W1997657677","https://openalex.org/W2073265902","https://openalex.org/W2127363101","https://openalex.org/W2139532006","https://openalex.org/W2169189540","https://openalex.org/W2390096555","https://openalex.org/W4250366158","https://openalex.org/W6635687051","https://openalex.org/W6635789232","https://openalex.org/W6711233619"],"related_works":["https://openalex.org/W2223855511","https://openalex.org/W2185312392","https://openalex.org/W1770021664","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/W2170377017"],"abstract_inverted_index":{"The":[0,15],"identification":[1,19,40],"of":[2,8,17,36,47],"duplicated":[3,37,80],"web":[4,38,81],"pages":[5,39,82],"is":[6],"one":[7],"the":[9,18,30,45,71,79,94],"related":[10],"steps":[11],"in":[12,41,83,98],"search":[13,22,42,99],"engine.":[14,43,100],"effect":[16],"will":[20],"affect":[21],"engine's":[23],"performance.":[24,57],"This":[25],"article":[26],"studies":[27],"and":[28,52,62],"summarizes":[29,59],"basic":[31,55],"processing":[32],"steps,":[33],"key":[34],"technologies":[35],"On":[44],"basis":[46],"some":[48,54],"experiments,":[49],"we":[50,65,90],"analyze":[51],"contrast":[53],"algorithms'":[56],"Then":[58],"their":[60],"advantages":[61],"disadvantages.":[63],"Finally,":[64],"proposes":[66],"an":[67],"idea":[68],"that":[69],"use":[70],"distributed":[72],"computing":[73],"such":[74],"as":[75],"Hadoop":[76],"to":[77,85,92],"identify":[78],"order":[84],"make":[86],"more":[87],"efficiency":[88],"when":[89],"try":[91],"process":[93],"massive":[95],"internet":[96],"information":[97]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
