{"id":"https://openalex.org/W1991804188","doi":"https://doi.org/10.1145/2065023.2065031","title":"Detection of near-duplicate user generated contents","display_name":"Detection of near-duplicate user generated contents","publication_year":2011,"publication_date":"2011-10-28","ids":{"openalex":"https://openalex.org/W1991804188","doi":"https://doi.org/10.1145/2065023.2065031","mag":"1991804188"},"language":"en","primary_location":{"id":"doi:10.1145/2065023.2065031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2065023.2065031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international workshop on Search and mining user-generated contents","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/A5109974716","display_name":"Enrique Vall\u00e9s","orcid":null},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Enrique Vall\u00e9s","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Valencia, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Valencia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053947754","display_name":"Paolo Rosso","orcid":"https://orcid.org/0000-0002-8922-1242"},"institutions":[{"id":"https://openalex.org/I60053951","display_name":"Universitat Polit\u00e8cnica de Val\u00e8ncia","ror":"https://ror.org/01460j859","country_code":"ES","type":"education","lineage":["https://openalex.org/I60053951"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Paolo Rosso","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Valencia, Valencia, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Valencia, Valencia, Spain","institution_ids":["https://openalex.org/I60053951"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109974716"],"corresponding_institution_ids":["https://openalex.org/I60053951"],"apc_list":null,"apc_paid":null,"fwci":8.8674,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.97299892,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"27","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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/T11644","display_name":"Spam and Phishing Detection","score":1.0,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.9994999766349792,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8129971027374268},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7128531336784363},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7120151519775391},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5960926413536072},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5937771797180176},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.565436065196991},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3887537717819214},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28655630350112915},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09283038973808289},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07594740390777588}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8129971027374268},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7128531336784363},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7120151519775391},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5960926413536072},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5937771797180176},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.565436065196991},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3887537717819214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28655630350112915},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09283038973808289},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07594740390777588},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2065023.2065031","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2065023.2065031","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international workshop on Search and mining user-generated contents","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310536","display_name":"University of Virginia","ror":"https://ror.org/0153tk833"},{"id":"https://openalex.org/F4320318602","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29"},{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W123495503","https://openalex.org/W166259489","https://openalex.org/W219410727","https://openalex.org/W1239002436","https://openalex.org/W1501099340","https://openalex.org/W1568686608","https://openalex.org/W1575272122","https://openalex.org/W1596691921","https://openalex.org/W1974719208","https://openalex.org/W1981745473","https://openalex.org/W1985895460","https://openalex.org/W1987380777","https://openalex.org/W1997665666","https://openalex.org/W2004025009","https://openalex.org/W2007842132","https://openalex.org/W2028776121","https://openalex.org/W2036166268","https://openalex.org/W2047756776","https://openalex.org/W2050612875","https://openalex.org/W2069985874","https://openalex.org/W2107227928","https://openalex.org/W2110166424","https://openalex.org/W2111295912","https://openalex.org/W2115023510","https://openalex.org/W2119672021","https://openalex.org/W2121135610","https://openalex.org/W2131438151","https://openalex.org/W2132069633","https://openalex.org/W2134168908","https://openalex.org/W2139532006","https://openalex.org/W2145349611","https://openalex.org/W2152565070","https://openalex.org/W2183705191","https://openalex.org/W2602449503","https://openalex.org/W2605134814","https://openalex.org/W2912431181","https://openalex.org/W2949957935","https://openalex.org/W4285719527","https://openalex.org/W6677643175","https://openalex.org/W6679663036","https://openalex.org/W6682678078"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W1834608617","https://openalex.org/W2384888906","https://openalex.org/W2376314740","https://openalex.org/W1999627569","https://openalex.org/W2366644548","https://openalex.org/W2380998760","https://openalex.org/W2357241418","https://openalex.org/W763609066","https://openalex.org/W2119214692"],"abstract_inverted_index":{"Today,":[0],"the":[1,20,69,102,107,123,140,144,165],"number":[2,153],"of":[3,29,46,64,71,81,109,154],"spam":[4,30,47,96,157],"text":[5,48,65,97],"messages":[6,31,49,158],"has":[7],"grown":[8],"in":[9],"number,":[10],"mainly":[11],"because":[12,39],"companies":[13],"are":[14,162],"looking":[15],"for":[16,95,132],"free":[17],"advertising.":[18],"For":[19],"users":[21],"is":[22,50],"very":[23,52],"important":[24],"to":[25,60],"filter":[26],"these":[27],"kinds":[28],"that":[32,127],"can":[33,74],"be":[34,75,91],"viewed":[35],"as":[36,77,93],"near-duplicate":[37,72,103,155],"texts":[38],"mostly":[40],"created":[41],"from":[42],"templates.":[43],"The":[44,135],"identification":[45],"a":[51,78,110,151],"hard":[53],"and":[54,57],"time-consuming":[55],"task":[56,70],"it":[58],"involves":[59],"carefully":[61],"scanning":[62],"hundreds":[63],"messages.":[66,98],"Therefore,":[67],"since":[68],"detection":[73,88,104,148],"seen":[76],"specific":[79],"case":[80],"plagiarism":[82,87,147],"detection,":[83],"we":[84,100],"investigated":[85],"whether":[86],"tools":[89,149],"could":[90],"used":[92],"filters":[94],"Moreover":[99],"solve":[101],"problem":[105],"on":[106,122],"basis":[108],"clustering":[111,167],"approach":[112],"using":[113],"CLUTO":[114,166],"framework.":[115],"We":[116],"carried":[117],"out":[118],"some":[119],"preliminary":[120],"experiments":[121],"SMS":[124,156],"Spam":[125],"Collection":[126],"recently":[128],"was":[129],"made":[130],"available":[131],"research":[133],"purposes.":[134],"results":[136,161],"were":[137],"compared":[138],"with":[139,143,164],"ones":[141],"obtained":[142,163],"CLUTO.":[145],"Althought":[146],"detect":[150],"good":[152],"even":[159],"better":[160],"tool.":[168]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
