{"id":"https://openalex.org/W2053017876","doi":"https://doi.org/10.1145/1277741.1277928","title":"Strategies for retrieving plagiarized documents","display_name":"Strategies for retrieving plagiarized documents","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2053017876","doi":"https://doi.org/10.1145/1277741.1277928","mag":"2053017876"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277928","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","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/A5027915931","display_name":"Benno Stein","orcid":"https://orcid.org/0000-0001-9033-2217"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Benno Stein","raw_affiliation_strings":["Bauhaus University Weimar, Weimar, Germany","Bauhaus-University Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus University Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]},{"raw_affiliation_string":"Bauhaus-University Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075956423","display_name":"Sven Meyer zu Eissen","orcid":null},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Sven Meyer zu Eissen","raw_affiliation_strings":["Bauhaus University Weimar, Weimar, Germany","Bauhaus-University Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus University Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]},{"raw_affiliation_string":"Bauhaus-University Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083712311","display_name":"Martin Potthast","orcid":"https://orcid.org/0000-0003-2451-0665"},"institutions":[{"id":"https://openalex.org/I51441396","display_name":"Bauhaus-Universit\u00e4t Weimar","ror":"https://ror.org/033bb5z47","country_code":"DE","type":"education","lineage":["https://openalex.org/I51441396"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Potthast","raw_affiliation_strings":["Bauhaus University Weimar, Weimar, Germany","Bauhaus-University Weimar, Weimar, Germany"],"affiliations":[{"raw_affiliation_string":"Bauhaus University Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]},{"raw_affiliation_string":"Bauhaus-University Weimar, Weimar, Germany","institution_ids":["https://openalex.org/I51441396"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027915931"],"corresponding_institution_ids":["https://openalex.org/I51441396"],"apc_list":null,"apc_paid":null,"fwci":7.7274,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":{"value":0.97084354,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"825","last_page":"826"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T10028","display_name":"Topic Modeling","score":0.9965999722480774,"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/T12478","display_name":"Wikis in Education and Collaboration","score":0.9790999889373779,"subfield":{"id":"https://openalex.org/subfields/3315","display_name":"Communication"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8070652484893799},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6406198143959045},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.632901668548584},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5673079490661621},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5415928363800049},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.5202678442001343},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.500316858291626},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.48394349217414856},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4338657557964325},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4233125150203705},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39401376247406006},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33918243646621704},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18412092328071594}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8070652484893799},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6406198143959045},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.632901668548584},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5673079490661621},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5415928363800049},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.5202678442001343},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.500316858291626},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.48394349217414856},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4338657557964325},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4233125150203705},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39401376247406006},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33918243646621704},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18412092328071594},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1277741.1277928","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W1556744446","https://openalex.org/W2120933912","https://openalex.org/W2129070169","https://openalex.org/W2164634022","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4240253816","https://openalex.org/W3096456556","https://openalex.org/W2169584677","https://openalex.org/W2979513934","https://openalex.org/W4232954277","https://openalex.org/W2020341030","https://openalex.org/W2749133591","https://openalex.org/W2367473450","https://openalex.org/W2358294942","https://openalex.org/W4367460280"],"abstract_inverted_index":{"For":[0],"the":[1,23],"identification":[2],"of":[3,38,60,68],"plagiarized":[4],"passages":[5],"in":[6,41,66],"large":[7],"document":[8],"collections":[9],"we":[10,27],"present":[11],"retrieval":[12],"strategies":[13],"which":[14],"rely":[15],"on":[16],"stochastic":[17],"sampling":[18],"and":[19,31,56,70],"chunk":[20],"indexes.":[21],"Using":[22],"entire":[24],"Wikipedia":[25],"corpus":[26],"compile":[28],"n-gram":[29],"indexes":[30],"compare":[32],"them":[33],"to":[34],"a":[35,42],"new":[36],"kind":[37],"fingerprint":[39],"index":[40,48],"plagiarism":[43],"analysis":[44,51],"use":[45],"case.":[46],"Our":[47],"provides":[49],"an":[50,58],"speed-up":[52],"by":[53],"factor":[54],"1.5":[55],"is":[57],"order":[59],"magnitude":[61],"smaller,":[62],"while":[63],"being":[64],"equivalent":[65],"terms":[67],"precision":[69],"recall.":[71]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":7}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}