{"id":"https://openalex.org/W2132260434","doi":"https://doi.org/10.1109/cit.2008.4594656","title":"The study on Detecting Near-Duplicate WebPages","display_name":"The study on Detecting Near-Duplicate WebPages","publication_year":2008,"publication_date":"2008-07-01","ids":{"openalex":"https://openalex.org/W2132260434","doi":"https://doi.org/10.1109/cit.2008.4594656","mag":"2132260434"},"language":"en","primary_location":{"id":"doi:10.1109/cit.2008.4594656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cit.2008.4594656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 8th IEEE International Conference on Computer and Information Technology","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/A5039234688","display_name":"Yujuan Cao","orcid":"https://orcid.org/0009-0001-0768-0534"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"YuJuan Cao","raw_affiliation_strings":["Beijing Institute of Technology, School of Computer Science and Technology, China","Sch. of Comput. Sci. Technol., Beijing Inst. of Technol., Beijing"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, School of Computer Science and Technology, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Sch. of Comput. Sci. Technol., Beijing Inst. of Technol., Beijing","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082774439","display_name":"Zhendong Niu","orcid":"https://orcid.org/0000-0002-0576-7572"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"ZhenDong Niu","raw_affiliation_strings":["Beijing Institute of Technology, School of Computer Science and Technology, China","Sch. of Comput. Sci. Technol., Beijing Inst. of Technol., Beijing"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, School of Computer Science and Technology, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Sch. of Comput. Sci. Technol., Beijing Inst. of Technol., Beijing","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100721601","display_name":"Weiqiang Wang","orcid":"https://orcid.org/0000-0002-7185-2804"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"WeiQiang Wang","raw_affiliation_strings":["Beijing Institute of Technology, School of Computer Science and Technology, China","Sch. of Comput. Sci. Technol., Beijing Inst. of Technol., Beijing"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, School of Computer Science and Technology, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Sch. of Comput. Sci. Technol., Beijing Inst. of Technol., Beijing","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006293645","display_name":"Kun Zhao","orcid":"https://orcid.org/0000-0001-5487-6532"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhao","raw_affiliation_strings":["Beijing Institute of Technology, School of Computer Science and Technology, China","Sch. of Comput. Sci. Technol., Beijing Inst. of Technol., Beijing"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology, School of Computer Science and Technology, China","institution_ids":["https://openalex.org/I125839683"]},{"raw_affiliation_string":"Sch. of Comput. Sci. Technol., Beijing Inst. of Technol., Beijing","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5039234688"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.13584618,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"95","last_page":"100"},"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":0.9972000122070312,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.8257651925086975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8226444721221924},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7329199314117432},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.48249363899230957},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4258393347263336},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3212842345237732}],"concepts":[{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8257651925086975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8226444721221924},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7329199314117432},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.48249363899230957},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4258393347263336},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3212842345237732},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cit.2008.4594656","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cit.2008.4594656","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 8th IEEE International Conference on Computer and Information Technology","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1941707302","https://openalex.org/W1974878721","https://openalex.org/W1997438973","https://openalex.org/W2007842132","https://openalex.org/W2067432306","https://openalex.org/W2087303323","https://openalex.org/W2111549955","https://openalex.org/W2127363101","https://openalex.org/W2133814403","https://openalex.org/W2139532006","https://openalex.org/W2145349611","https://openalex.org/W2152565070","https://openalex.org/W2153180170","https://openalex.org/W2164634022","https://openalex.org/W2165612380","https://openalex.org/W2169189540","https://openalex.org/W2564732998","https://openalex.org/W4250366158"],"related_works":["https://openalex.org/W1488511360","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723","https://openalex.org/W188332989","https://openalex.org/W2982387199","https://openalex.org/W2000745862","https://openalex.org/W2120930843","https://openalex.org/W42013907","https://openalex.org/W2042734105"],"abstract_inverted_index":{"Reprinting":[0],"information":[1,52],"among":[2],"websites":[3],"produces":[4],"a":[5,31,36],"great":[6],"deal":[7],"redundant":[8],"WebPages.":[9],"To":[10],"improve":[11],"search":[12,73],"efficiency":[13],"and":[14,50,55,126],"user":[15],"satisfaction,":[16],"an":[17,98],"algorithm":[18],"to":[19,53],"Detect":[20],"near-Duplicate":[21],"WebPages":[22,92],"(DDW)":[23],"is":[24],"proposed.":[25],"In":[26,120],"the":[27,78,107],"course":[28],"of":[29],"developing":[30],"near-duplicate":[32,91],"detection":[33],"system":[34],"for":[35,74,85],"multi-billion":[37],"page":[38],"repository,":[39],"we":[40,46,66,88],"make":[41],"two":[42],"research":[43],"contributions.":[44],"First,":[45],"consider":[47],"both":[48],"syntactic":[49],"semantic":[51],"present":[54],"compute":[56],"documentspsila":[57],"similarities.":[58],"Second,":[59],"after":[60],"classifying":[61],"web-pages":[62],"into":[63,97],"different":[64],"categories,":[65],"index":[67],"feature":[68],"in":[69,77],"each":[70],"category":[71],"then":[72],"near-duplicates":[75],"only":[76],"same":[79],"category.":[80],"From":[81],"Google":[82],"searching":[83],"results":[84,112],"72":[86],"queries,":[87],"select":[89],"5835":[90],"manually.":[93],"Then":[94],"insert":[95],"them":[96],"existing":[99],"collection":[100],"which":[101],"contains":[102],"about":[103],"768,763":[104],"WebPages,":[105],"as":[106],"test":[108],"data.":[109],"The":[110],"experimental":[111],"demonstrate":[113],"that":[114],"our":[115],"approach":[116],"outperforms":[117],"I-Match":[118],"algorithms.":[119],"large-scale":[121],"test,":[122],"approximate":[123],"linear":[124],"time":[125],"space":[127],"complexity":[128],"are":[129],"gotten.":[130]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
