{"id":"https://openalex.org/W2001504893","doi":"https://doi.org/10.1109/icdim.2009.5356801","title":"Effectively and efficiently detect web page duplication","display_name":"Effectively and efficiently detect web page duplication","publication_year":2009,"publication_date":"2009-11-01","ids":{"openalex":"https://openalex.org/W2001504893","doi":"https://doi.org/10.1109/icdim.2009.5356801","mag":"2001504893"},"language":"en","primary_location":{"id":"doi:10.1109/icdim.2009.5356801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2009.5356801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 Fourth International Conference on Digital Information Management","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/A5047135195","display_name":"Zhongming Han","orcid":"https://orcid.org/0000-0003-0119-2828"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongming Han","raw_affiliation_strings":["School of computer science and information engineering, Beijing Technology and Business University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of computer science and information engineering, Beijing Technology and Business University, Beijing, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007849859","display_name":"Qian Mo","orcid":"https://orcid.org/0009-0009-7025-2012"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Mo","raw_affiliation_strings":["School of computer science and information engineering, Beijing Technology and Business University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of computer science and information engineering, Beijing Technology and Business University, Beijing, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100679042","display_name":"Hongzhi Liu","orcid":"https://orcid.org/0000-0001-6216-0796"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhi Liu","raw_affiliation_strings":["School of computer science and information engineering, Beijing Technology and Business University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of computer science and information engineering, Beijing Technology and Business University, Beijing, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083236307","display_name":"Jianzhi Sun","orcid":"https://orcid.org/0009-0003-6014-7549"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianzhi Sun","raw_affiliation_strings":["School of computer science and information engineering, Beijing Technology and Business University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of computer science and information engineering, Beijing Technology and Business University, Beijing, China","institution_ids":["https://openalex.org/I179026463"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I179026463"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"4","issue":null,"first_page":"1","last_page":"6"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9886999726295471,"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/computer-science","display_name":"Computer science","score":0.8359677195549011},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7548360824584961},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.6974036693572998},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6582568287849426},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6016445159912109},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5573025345802307},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.45777106285095215},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.42370346188545227},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34006771445274353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2040739357471466},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.13590207695960999},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10995778441429138},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09139102697372437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8359677195549011},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7548360824584961},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.6974036693572998},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6582568287849426},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6016445159912109},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5573025345802307},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.45777106285095215},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.42370346188545227},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34006771445274353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2040739357471466},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.13590207695960999},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10995778441429138},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09139102697372437},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdim.2009.5356801","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdim.2009.5356801","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 Fourth International Conference on Digital Information Management","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":15,"referenced_works":["https://openalex.org/W1487292165","https://openalex.org/W1499420850","https://openalex.org/W1596691921","https://openalex.org/W1609518033","https://openalex.org/W1971652947","https://openalex.org/W1972492617","https://openalex.org/W1997438973","https://openalex.org/W2085922539","https://openalex.org/W2125570474","https://openalex.org/W2139532006","https://openalex.org/W2149037431","https://openalex.org/W2169189540","https://openalex.org/W2353539429","https://openalex.org/W3098786064","https://openalex.org/W4244354591"],"related_works":["https://openalex.org/W1979144454","https://openalex.org/W4239898202","https://openalex.org/W2069679074","https://openalex.org/W2115253914","https://openalex.org/W3116613346","https://openalex.org/W4237456423","https://openalex.org/W2911454453","https://openalex.org/W2055154498","https://openalex.org/W1559090489","https://openalex.org/W2351131669"],"abstract_inverted_index":{"There":[0],"are":[1],"a":[2,20],"lot":[3],"of":[4],"redundant":[5],"Web":[6,27,58],"pages":[7,28,59],"on":[8,11],"Internet.":[9],"Based":[10],"tag":[12,66],"statistic":[13,67],"and":[14,40,68],"text":[15,36,69],"similarity":[16,35],"comparison,":[17],"we":[18],"present":[19],"novel":[21],"multilayer":[22],"framework":[23],"for":[24],"detecting":[25],"duplicated":[26,57],"in":[29],"this":[30],"paper.":[31],"We":[32],"propose":[33],"two":[34],"paragraphs":[37],"detection":[38],"algorithms":[39],"implement":[41],"our":[42,49],"framework.":[43],"The":[44],"experimental":[45],"results":[46],"show":[47],"that":[48,56],"approach":[50],"achieves":[51],"high":[52],"performance,":[53],"which":[54],"means":[55],"can":[60],"be":[61],"efficiently":[62],"detected":[63],"simply":[64],"by":[65],"comparison.":[70]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
