{"id":"https://openalex.org/W2109037014","doi":"https://doi.org/10.11591/ijece.v1i2.77","title":"An Efficient Approach for Finding Near Duplicate Web pages using Minimum Weight Overlapping Method","display_name":"An Efficient Approach for Finding Near Duplicate Web pages using Minimum Weight Overlapping Method","publication_year":2011,"publication_date":"2011-10-29","ids":{"openalex":"https://openalex.org/W2109037014","doi":"https://doi.org/10.11591/ijece.v1i2.77","mag":"2109037014"},"language":"en","primary_location":{"id":"doi:10.11591/ijece.v1i2.77","doi":"https://doi.org/10.11591/ijece.v1i2.77","is_oa":true,"landing_page_url":"https://doi.org/10.11591/ijece.v1i2.77","pdf_url":null,"source":{"id":"https://openalex.org/S2764532672","display_name":"International Journal of Electrical and Computer Engineering (IJECE)","issn_l":"2088-8708","issn":["2088-8708"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Electrical and Computer Engineering (IJECE)","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.11591/ijece.v1i2.77","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079630818","display_name":"Shine N Das","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20497027","display_name":"Cochin University of Science and Technology","ror":"https://ror.org/00a4kqq17","country_code":"IN","type":"education","lineage":["https://openalex.org/I20497027"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shine N Das","raw_affiliation_strings":["Dept. of Comput. Applic., CUSAT, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Applic., CUSAT, India","institution_ids":["https://openalex.org/I20497027"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031198524","display_name":"Midhun P Mathew","orcid":"https://orcid.org/0000-0003-2248-0124","observed_orcids":["https://orcid.org/0000-0003-2248-0124"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Midhun Mathew","raw_affiliation_strings":["MBITS"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MBITS","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039106467","display_name":"Pramod K. Vijayaraghavan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20497027","display_name":"Cochin University of Science and Technology","ror":"https://ror.org/00a4kqq17","country_code":"IN","type":"education","lineage":["https://openalex.org/I20497027"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pramod K. Vijayaraghavan","raw_affiliation_strings":["CUSAT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CUSAT","institution_ids":["https://openalex.org/I20497027"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5028,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73416027,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"1","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.6182000041007996,"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":0.6182000041007996,"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/T11719","display_name":"Data Quality and Management","score":0.1981000006198883,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.07890000194311142,"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/duplicate-detection","display_name":"duplicate detection","score":0.7099999785423279},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"plagiarism detection","score":0.878000020980835},{"id":"https://openalex.org/keywords/spam-detection","display_name":"spam detection","score":0.8999999761581421},{"id":"https://openalex.org/keywords/focused-web-crawling","display_name":"focused web crawling","score":0.9309999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7551261186599731},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37893617153167725},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.363244891166687}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.11591/ijece.v1i2.77","doi":"https://doi.org/10.11591/ijece.v1i2.77","is_oa":true,"landing_page_url":"https://doi.org/10.11591/ijece.v1i2.77","pdf_url":null,"source":{"id":"https://openalex.org/S2764532672","display_name":"International Journal of Electrical and Computer Engineering (IJECE)","issn_l":"2088-8708","issn":["2088-8708"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Electrical and Computer Engineering (IJECE)","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.300.7544","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.300.7544","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://iaesjournal.com/online/index.php/IJECE/article/viewFile/77/pdf/","raw_type":"text"}],"best_oa_location":{"id":"doi:10.11591/ijece.v1i2.77","doi":"https://doi.org/10.11591/ijece.v1i2.77","is_oa":true,"landing_page_url":"https://doi.org/10.11591/ijece.v1i2.77","pdf_url":null,"source":{"id":"https://openalex.org/S2764532672","display_name":"International Journal of Electrical and Computer Engineering (IJECE)","issn_l":"2088-8708","issn":["2088-8708"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-1","poland-70","russia-white-list-2","vabb-shw"],"host_organization":"https://openalex.org/P4310315009","host_organization_name":"Institute of Advanced Engineering and Science (IAES)","host_organization_lineage":["https://openalex.org/P4310315009"],"host_organization_lineage_names":["Institute of Advanced Engineering and Science (IAES)"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Electrical and Computer Engineering (IJECE)","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2050612875","https://openalex.org/W7099493317","https://openalex.org/W2037655662","https://openalex.org/W2008577673","https://openalex.org/W2132260434","https://openalex.org/W1965704641","https://openalex.org/W2124313537","https://openalex.org/W1575272122","https://openalex.org/W7098011050","https://openalex.org/W7097384394"],"abstract_inverted_index":{"The":[0,17,201],"existence":[1,46],"of":[2,4,14,19,47,87,108,128,173,185,211,224],"billions":[3],"web":[5,15,22,99,115,131,155,188],"data":[6,34],"has":[7],"severely":[8],"affected":[9],"the":[10,45,53,60,74,79,85,106,171,177,191,222],"performance":[11,30],"and":[12,57,69,113,149,157,166,180,216,218],"reliability":[13],"search.":[16],"presence":[18],"near":[20,97,126,186],"duplicate":[21,98,187],"pages":[23,51,100,189],"plays":[24],"an":[25,121,129,153,182],"important":[26],"role":[27],"in":[28,105,160,176,190,209,221],"this":[29],"degradation":[31],"while":[32],"integrating":[33],"from":[35,73,133],"heterogeneous":[36],"sources.":[37],"Web":[38,75],"mining":[39],"faces":[40],"huge":[41,135],"problems":[42],"due":[43],"to":[44,67,169],"such":[48,71],"documents.":[49],"These":[50],"increase":[52,59],"index":[54],"storage":[55],"space":[56],"thereby":[58],"serving":[61],"cost.":[62],"By":[63],"introducing":[64],"efficient":[65,122],"methods":[66],"detect":[68],"remove":[70],"documents":[72],"not":[76],"only":[77],"decreases":[78],"computation":[80],"time":[81],"but":[82],"also":[83],"increases":[84],"relevancy":[86],"search":[88],"results.":[89],"We":[90],"aim":[91],"a":[92,134,158,219],"novel":[93],"idea":[94],"for":[95,124],"finding":[96,125],"which":[101,151],"can":[102],"be":[103],"incorporated":[104],"field":[107],"plagiarism":[109],"detection,":[110],"spam":[111],"detection":[112],"focused":[114],"crawling":[116],"scenarios.":[117],"Here":[118],"we":[119],"propose":[120],"method":[123],"duplicates":[127],"input":[130,154],"page,":[132],"repository.":[136],"A":[137],"TDW":[138],"matrix":[139],"based":[140],"algorithm":[141,207],"is":[142],"proposed":[143],"with":[144],"three":[145],"phases,":[146],"rendering,":[147],"filtering":[148,165,168],"verification,":[150],"receives":[152],"page":[156],"threshold":[159],"its":[161],"first":[162],"phase,":[163],"prefix":[164],"positional":[167],"reduce":[170],"size":[172,223],"record":[174,226],"set":[175,184],"second":[178],"phase":[179,193],"returns":[181],"optimal":[183],"verification":[192],"by":[194],"using":[195],"Minimum":[196],"Weight":[197],"Overlapping":[198],"(MWO)":[199],"method.":[200],"experimental":[202],"results":[203],"show":[204],"that":[205],"our":[206],"outperforms":[208],"terms":[210],"two":[212],"benchmark":[213],"measures,":[214],"precision":[215],"recall,":[217],"reduction":[220],"competing":[225],"set.":[227]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2016-06-24T00:00:00"}
