{"id":"https://openalex.org/W384178481","doi":null,"title":"Plagiarism detection by similarity join","display_name":"Plagiarism detection by similarity join","publication_year":2009,"publication_date":"2009-08-18","ids":{"openalex":"https://openalex.org/W384178481","mag":"384178481"},"language":"en","primary_location":{"id":"pmh:oai:tudelft.nl:uuid:a18b62c5-e73e-44fc-9336-83a78275f266","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:a18b62c5-e73e-44fc-9336-83a78275f266","pdf_url":"https://repository.tudelft.nl/file/File_9ec7e57a-52e6-46f0-a0ed-835c3c023ed6","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.tudelft.nl/file/File_9ec7e57a-52e6-46f0-a0ed-835c3c023ed6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072899738","display_name":"R. Schellenberger","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"R. Schellenberger","raw_affiliation_strings":["Delft University of Technology,,,,,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology,,,,,","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5072899738"],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.7993000149726868,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.7993000149726868,"subfield":{"id":"https://openalex.org/subfields/3304","display_name":"Education"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.042399998754262924,"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/T10260","display_name":"Software Engineering Research","score":0.03660000115633011,"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/plagiarism-detection","display_name":"plagiarism detection","score":0.9980000257492065},{"id":"https://openalex.org/keywords/similarity-join","display_name":"similarity join","score":0.9879999756813049},{"id":"https://openalex.org/keywords/prefiltering","display_name":"pre-filtering","score":0.8579999804496765},{"id":"https://openalex.org/keywords/online-news-articles","display_name":"online news articles","score":0.828000009059906},{"id":"https://openalex.org/keywords/text-reuse-detection","display_name":"text reuse detection","score":0.5299999713897705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058643341064453},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6577776074409485},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6194627285003662},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.5947243571281433},{"id":"https://openalex.org/C41458344","wikidata":"https://www.wikidata.org/wiki/Q732577","display_name":"Publication","level":2,"score":0.5024445056915283},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4805901050567627},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.45869866013526917},{"id":"https://openalex.org/C2779089604","wikidata":"https://www.wikidata.org/wiki/Q7169333","display_name":"Permission","level":2,"score":0.4573255777359009},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.43933597207069397},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.437389075756073},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.41820842027664185},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.41344523429870605},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3205808997154236},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23510393500328064},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17786860466003418},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.11885631084442139},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:tudelft.nl:uuid:a18b62c5-e73e-44fc-9336-83a78275f266","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:a18b62c5-e73e-44fc-9336-83a78275f266","pdf_url":"https://repository.tudelft.nl/file/File_9ec7e57a-52e6-46f0-a0ed-835c3c023ed6","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},{"id":"mag:384178481","doi":null,"is_oa":false,"landing_page_url":"http://resolver.tudelft.nl/uuid:a18b62c5-e73e-44fc-9336-83a78275f266","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:tudelft.nl:uuid:a18b62c5-e73e-44fc-9336-83a78275f266","doi":null,"is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:a18b62c5-e73e-44fc-9336-83a78275f266","pdf_url":"https://repository.tudelft.nl/file/File_9ec7e57a-52e6-46f0-a0ed-835c3c023ed6","source":{"id":"https://openalex.org/S4306400906","display_name":"Research Repository (Delft University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I98358874","host_organization_name":"Delft University of Technology","host_organization_lineage":["https://openalex.org/I98358874"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"master thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W384178481.pdf","grobid_xml":"https://content.openalex.org/works/W384178481.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1536700701","https://openalex.org/W1609518033","https://openalex.org/W1742907023","https://openalex.org/W1961258751","https://openalex.org/W1965657003","https://openalex.org/W1971525887","https://openalex.org/W1980300190","https://openalex.org/W2007842132","https://openalex.org/W2008434289","https://openalex.org/W2026968007","https://openalex.org/W2035950535","https://openalex.org/W2053017876","https://openalex.org/W2067432306","https://openalex.org/W2084367148","https://openalex.org/W2087619740","https://openalex.org/W2095728454","https://openalex.org/W2097184821","https://openalex.org/W2101388432","https://openalex.org/W2109803107","https://openalex.org/W2111295912","https://openalex.org/W2111549955","https://openalex.org/W2138662031","https://openalex.org/W2145349611","https://openalex.org/W2148885851","https://openalex.org/W2152565070","https://openalex.org/W2164634022"],"related_works":["https://openalex.org/W3167277189","https://openalex.org/W2047666654","https://openalex.org/W2783043502","https://openalex.org/W1972649625","https://openalex.org/W2143334511","https://openalex.org/W3087977254","https://openalex.org/W1980863348","https://openalex.org/W2573878356","https://openalex.org/W2091011608","https://openalex.org/W7095241773"],"abstract_inverted_index":{"Since":[0],"the":[1,21,81,107,135],"internet":[2],"is":[3,11,14,125,138],"so":[4,34],"big":[5],"and":[6,36,76,94,121,144],"most":[7],"of":[8,42,72,118,149,153],"its":[9],"content":[10],"public,":[12],"it":[13,140],"very":[15],"hard":[16],"to":[17,63,104,110,129],"find":[18],"out":[19],"where":[20,43],"information":[22],"came":[23],"from":[24],"originally.":[25],"There":[26],"are":[27,46],"many":[28],"websites":[29],"that":[30,60],"publish":[31],"news":[32,67,74],"articles,":[33],"people":[35],"organizations":[37],"can":[38],"easily":[39],"lose":[40],"track":[41],"their":[44,51],"articles":[45,68,75],"reused":[47],"with":[48,69,80],"or":[49],"without":[50],"permission.":[52],"This":[53],"paper":[54],"presents":[55],"a":[56,70,85,90,95,99,111,116,147],"plagiarism":[57],"detection":[58],"algorithm":[59,88,114],"allows":[61],"us":[62],"quickly":[64],"compare":[65],"online":[66],"collection":[71],"personal":[73],"detect":[77],"plagiarized":[78],"passages":[79],"same":[82],"quality":[83],"as":[84,98],"human.":[86],"The":[87,113],"uses":[89],"basic":[91],"shingle":[92],"index":[93],"Signature":[96],"Tree":[97],"more":[100],"advanced":[101],"pre-filtering":[102,136],"step":[103,137],"narrow":[105],"down":[106],"viable":[108],"documents":[109],"query.":[112],"achieves":[115,141],"score":[117],"0.96":[119],"precision":[120,143],"0.94":[122],"recall":[123,145],"but":[124],"too":[126],"resource":[127],"intensive":[128],"be":[130],"considered":[131],"scalable.":[132],"When":[133],"only":[134],"used,":[139],"0.85":[142],"creating":[146],"speedup":[148],"nearly":[150],"one":[151],"order":[152],"magnitude.":[154]},"counts_by_year":[],"updated_date":"2026-09-09T07:26:56.047234","created_date":"2016-06-24T00:00:00"}
