{"id":"https://openalex.org/W2124064358","doi":"https://doi.org/10.1109/laweb.2003.1250297","title":"Syntactic similarity of Web documents","display_name":"Syntactic similarity of Web documents","publication_year":2004,"publication_date":"2004-05-06","ids":{"openalex":"https://openalex.org/W2124064358","doi":"https://doi.org/10.1109/laweb.2003.1250297","mag":"2124064358"},"language":"en","primary_location":{"id":"doi:10.1109/laweb.2003.1250297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/laweb.2003.1250297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/LEOS 3rd International Conference on Numerical Simulation of Semiconductor Optoelectronic Devices (IEEE Cat. No.03EX726)","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/A5105936082","display_name":"\u00c1lvaro Pereira","orcid":null},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"A.R. Pereira","raw_affiliation_strings":["Department of Computer Science, Federal University of Minas Gerais, Belo Horizonte, Brazil","Dept. of Comput. Sci., Fed.. Univ. of Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Fed.. Univ. of Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067195269","display_name":"N\u00edvio Ziviani","orcid":"https://orcid.org/0000-0002-7079-2010"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"N. Ziviani","raw_affiliation_strings":["Department of Computer Science, Federal University of Minas Gerais, Belo Horizonte, Brazil","Dept. of Comput. Sci., Fed.. Univ. of Minas Gerais, Belo Horizonte, Brazil"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University of Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Fed.. Univ. of Minas Gerais, Belo Horizonte, Brazil","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5105936082"],"corresponding_institution_ids":["https://openalex.org/I110200422"],"apc_list":null,"apc_paid":null,"fwci":1.8485,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.88052357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"194","last_page":"200"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994000196456909,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980000257492065,"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":0.7616196870803833},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7486790418624878},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6805863380432129},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5423532128334045},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.46775174140930176},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4440983235836029},{"id":"https://openalex.org/keywords/jaccard-index","display_name":"Jaccard index","score":0.44266921281814575},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.43896228075027466},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.42312559485435486},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4037691056728363},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3047516644001007},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.22035622596740723},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16824296116828918}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7616196870803833},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7486790418624878},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6805863380432129},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5423532128334045},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.46775174140930176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4440983235836029},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.44266921281814575},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.43896228075027466},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.42312559485435486},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4037691056728363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3047516644001007},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.22035622596740723},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16824296116828918},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/laweb.2003.1250297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/laweb.2003.1250297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE/LEOS 3rd International Conference on Numerical Simulation of Semiconductor Optoelectronic Devices (IEEE Cat. No.03EX726)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.6.305","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.6.305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cwr.cl/la-web/stamped/23_pereira_a.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1573714593","https://openalex.org/W1596691921","https://openalex.org/W1997841190","https://openalex.org/W2007842132","https://openalex.org/W2059513841","https://openalex.org/W2079721227","https://openalex.org/W2113958639","https://openalex.org/W2132069633","https://openalex.org/W2148044665","https://openalex.org/W2155512447","https://openalex.org/W2158874082","https://openalex.org/W2161532103","https://openalex.org/W2970408101","https://openalex.org/W6635789232","https://openalex.org/W6677099382","https://openalex.org/W6683646574"],"related_works":["https://openalex.org/W1994775821","https://openalex.org/W2012019886","https://openalex.org/W2091133150","https://openalex.org/W2945869148","https://openalex.org/W2398781203","https://openalex.org/W2009279505","https://openalex.org/W4206503171","https://openalex.org/W4366711670","https://openalex.org/W2558988915","https://openalex.org/W2972216353"],"abstract_inverted_index":{"We":[0],"present":[1],"and":[2,25,55,80,125,138],"compare":[3],"two":[4,83],"methods":[5,84],"for":[6,51],"evaluating":[7],"the":[8,17,22,26,31,38,48,59,93,112,115,119,123,128,139],"syntactic":[9],"similarity":[10,27,49,90],"between":[11,122],"documents.":[12],"The":[13,40],"first":[14],"method":[15,42],"uses":[16,43,131,142],"Patricia":[18,143],"tree,":[19],"constructed":[20],"from":[21,58,107,111],"original":[23,60,78,94],"document,":[24],"is":[28,62],"computed":[29],"searching":[30],"text":[32],"of":[33,70,118,136,147],"each":[34,56,71],"candidate":[35,72],"document":[36,53,61,73,79],"in":[37,64],"tree.":[39],"second":[41],"shingles":[44,69,132],"concept":[45],"to":[46],"obtain":[47],"measure":[50],"every":[52],"pairs,":[54],"shingle":[57],"inserted":[63],"a":[65,102,134,145],"hash":[66],"table,":[67],"where":[68],"are":[74],"searched.":[75],"Given":[76],"an":[77],"some":[81,89],"candidates,":[82],"find":[85],"documents":[86,104,109],"that":[87,130,141],"have":[88],"relationship":[91],"with":[92],"document.":[95],"Experimental":[96],"results":[97],"were":[98],"obtained":[99,126,133],"by":[100],"using":[101],"plagiarized":[103],"generator":[105],"system,":[106],"900":[108],"collected":[110],"Web.":[113],"Considering":[114],"arithmetic":[116],"average":[117],"absolute":[120],"differences":[121],"expected":[124],"similarity,":[127],"algorithm":[129,140],"performance":[135,146],"4.13%":[137],"tree":[144],"7.50%.":[148]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}