{"id":"https://openalex.org/W1992047625","doi":"https://doi.org/10.1109/cit.2008.4594721","title":"A new method on the detection of near-replicas of web pages","display_name":"A new method on the detection of near-replicas of web pages","publication_year":2008,"publication_date":"2008-07-01","ids":{"openalex":"https://openalex.org/W1992047625","doi":"https://doi.org/10.1109/cit.2008.4594721","mag":"1992047625"},"language":"en","primary_location":{"id":"doi:10.1109/cit.2008.4594721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cit.2008.4594721","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":null,"display_name":"Jia-heng Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jia-heng Zheng","raw_affiliation_strings":["Department of Computer and Information Technology of Shanxi University, Taiyuan, China, 030006","Dept. of Comput. & Inf. Technol., Shanxi Univ., Taiyuan"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology of Shanxi University, Taiyuan, China, 030006","institution_ids":["https://openalex.org/I181877577"]},{"raw_affiliation_string":"Dept. of Comput. & Inf. Technol., Shanxi Univ., Taiyuan","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101807961","display_name":"Lixia Wei","orcid":"https://orcid.org/0000-0003-2116-2394"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li-xia Wei","raw_affiliation_strings":["Department of Computer and Information Technology of Shanxi University, Taiyuan, China, 030006","Dept. of Comput. & Inf. Technol., Shanxi Univ., Taiyuan"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology of Shanxi University, Taiyuan, China, 030006","institution_ids":["https://openalex.org/I181877577"]},{"raw_affiliation_string":"Dept. of Comput. & Inf. Technol., Shanxi Univ., Taiyuan","institution_ids":["https://openalex.org/I181877577"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100751510","display_name":"Hongye Tan","orcid":"https://orcid.org/0000-0002-5858-899X"},"institutions":[{"id":"https://openalex.org/I181877577","display_name":"Shanxi University","ror":"https://ror.org/03y3e3s17","country_code":"CN","type":"education","lineage":["https://openalex.org/I181877577"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong-ye Tan","raw_affiliation_strings":["Department of Computer and Information Technology of Shanxi University, Taiyuan, China, 030006","Dept. of Comput. & Inf. Technol., Shanxi Univ., Taiyuan"],"affiliations":[{"raw_affiliation_string":"Department of Computer and Information Technology of Shanxi University, Taiyuan, China, 030006","institution_ids":["https://openalex.org/I181877577"]},{"raw_affiliation_string":"Dept. of Comput. & Inf. Technol., Shanxi Univ., Taiyuan","institution_ids":["https://openalex.org/I181877577"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181877577"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10727777,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"473","last_page":"478"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9742000102996826,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9595000147819519,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7640117406845093},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7041577100753784},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.666748583316803},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6120225787162781},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5854502320289612},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5372400879859924},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.49884819984436035},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4800075888633728},{"id":"https://openalex.org/keywords/hits-algorithm","display_name":"HITS algorithm","score":0.4333055019378662},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4262215495109558},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3780152499675751},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.3313223421573639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22715026140213013},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.21586570143699646},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.14367958903312683}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7640117406845093},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7041577100753784},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.666748583316803},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6120225787162781},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5854502320289612},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5372400879859924},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.49884819984436035},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4800075888633728},{"id":"https://openalex.org/C195409031","wikidata":"https://www.wikidata.org/wiki/Q1031957","display_name":"HITS algorithm","level":5,"score":0.4333055019378662},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4262215495109558},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3780152499675751},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.3313223421573639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22715026140213013},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.21586570143699646},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.14367958903312683},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","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},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cit.2008.4594721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cit.2008.4594721","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":0.4300000071525574,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1609518033","https://openalex.org/W1997657677","https://openalex.org/W2141359307","https://openalex.org/W2152565070"],"related_works":["https://openalex.org/W2387616437","https://openalex.org/W1588416135","https://openalex.org/W2008577673","https://openalex.org/W2295656603","https://openalex.org/W4254300012","https://openalex.org/W2096839908","https://openalex.org/W1486482441","https://openalex.org/W1999548128","https://openalex.org/W1536079598","https://openalex.org/W2156928086"],"abstract_inverted_index":{"Near-replicas":[0],"of":[1,9,24,30,45],"web":[2,25,34],"pages":[3,35],"have":[4],"seriously":[5],"decreased":[6],"the":[7,28,43,46,54,65,72,76,87],"efficiency":[8,89],"search":[10],"engine":[11],"(SE).":[12],"In":[13],"this":[14,81],"paper,":[15],"we":[16],"present":[17],"a":[18,62],"new":[19],"method":[20,82],"to":[21,42,52],"detect":[22],"near-replicas":[23],"pages.":[26],"Firstly,":[27],"styles":[29,44],"text":[31,55],"structures":[32],"in":[33],"are":[36,50],"analyzed":[37],"and":[38,95],"classified;":[39],"then":[40],"according":[41],"text,":[47],"different":[48],"methods":[49],"used":[51],"get":[53],"structure,":[56],"which":[57],"will":[58,67],"be":[59,68],"represented":[60],"as":[61],"matrix;":[63],"Finally,":[64],"similarity":[66],"calculated":[69],"by":[70],"extracting":[71],"features":[73],"dynamically":[74],"from":[75],"matrix.":[77],"Experiments":[78],"show":[79],"that":[80],"can":[83],"not":[84],"only":[85],"improve":[86],"computing":[88],"but":[90],"also":[91],"ensure":[92],"high":[93],"precision":[94],"recall.":[96]},"counts_by_year":[],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}
