{"id":"https://openalex.org/W2095728454","doi":"https://doi.org/10.1145/1086339.1086341","title":"Sentence-based natural language plagiarism detection","display_name":"Sentence-based natural language plagiarism detection","publication_year":2004,"publication_date":"2004-12-01","ids":{"openalex":"https://openalex.org/W2095728454","doi":"https://doi.org/10.1145/1086339.1086341","mag":"2095728454"},"language":"en","primary_location":{"id":"doi:10.1145/1086339.1086341","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1086339.1086341","pdf_url":null,"source":{"id":"https://openalex.org/S4210208609","display_name":"Journal on Educational Resources in Computing","issn_l":"1531-4278","issn":["1531-4278"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Educational Resources in Computing","raw_type":"journal-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/A5053926669","display_name":"Daniel White","orcid":"https://orcid.org/0000-0002-1032-4100"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel R. White","raw_affiliation_strings":["University of Warwick, Coventry, United Kingdom","University of Warwick Coventry , United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick, Coventry, United Kingdom","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"University of Warwick Coventry , United Kingdom","institution_ids":["https://openalex.org/I39555362"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012585972","display_name":"Mike Joy","orcid":"https://orcid.org/0000-0001-9826-5928"},"institutions":[{"id":"https://openalex.org/I39555362","display_name":"University of Warwick","ror":"https://ror.org/01a77tt86","country_code":"GB","type":"education","lineage":["https://openalex.org/I39555362"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mike S. Joy","raw_affiliation_strings":["University of Warwick, Coventry, United Kingdom","University of Warwick Coventry , United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Warwick, Coventry, United Kingdom","institution_ids":["https://openalex.org/I39555362"]},{"raw_affiliation_string":"University of Warwick Coventry , United Kingdom","institution_ids":["https://openalex.org/I39555362"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4198,"has_fulltext":false,"cited_by_count":61,"citation_normalized_percentile":{"value":0.9077092,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"4","issue":"4","first_page":"2","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"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/T10260","display_name":"Software Engineering Research","score":0.9929999709129333,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9435999989509583,"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/plagiarism-detection","display_name":"Plagiarism detection","score":0.882590651512146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.81773841381073},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.7885830402374268},{"id":"https://openalex.org/keywords/suspect","display_name":"Suspect","score":0.7358313202857971},{"id":"https://openalex.org/keywords/obfuscation","display_name":"Obfuscation","score":0.6825048923492432},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6167514324188232},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5613714456558228},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5380043983459473},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5165385603904724},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.5032116770744324},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49208515882492065},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4696582853794098},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.4689236283302307},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3344709873199463},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.162604421377182},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.07990503311157227}],"concepts":[{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.882590651512146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.81773841381073},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.7885830402374268},{"id":"https://openalex.org/C2778223634","wikidata":"https://www.wikidata.org/wiki/Q224952","display_name":"Suspect","level":2,"score":0.7358313202857971},{"id":"https://openalex.org/C40305131","wikidata":"https://www.wikidata.org/wiki/Q2616305","display_name":"Obfuscation","level":2,"score":0.6825048923492432},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6167514324188232},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5613714456558228},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5380043983459473},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5165385603904724},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.5032116770744324},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49208515882492065},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4696582853794098},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.4689236283302307},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3344709873199463},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.162604421377182},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.07990503311157227},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C73484699","wikidata":"https://www.wikidata.org/wiki/Q161733","display_name":"Criminology","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1086339.1086341","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1086339.1086341","pdf_url":null,"source":{"id":"https://openalex.org/S4210208609","display_name":"Journal on Educational Resources in Computing","issn_l":"1531-4278","issn":["1531-4278"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal on Educational Resources in Computing","raw_type":"journal-article"},{"id":"pmh:oai:wrap.warwick.ac.uk:61347","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400665","display_name":"Warwick Research Archive Portal (University of Warwick)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I39555362","host_organization_name":"University of Warwick","host_organization_lineage":["https://openalex.org/I39555362"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.463.2946","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.463.2946","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.dcs.warwick.ac.uk/302/1/white_joy_jeric04.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8899999856948853,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1515857294","https://openalex.org/W1557168499","https://openalex.org/W2083209617","https://openalex.org/W2096147520","https://openalex.org/W2113958639","https://openalex.org/W2132148174","https://openalex.org/W2146659255","https://openalex.org/W2148484595","https://openalex.org/W2160484851","https://openalex.org/W2161532103","https://openalex.org/W2163840964","https://openalex.org/W2164634022","https://openalex.org/W2578190765","https://openalex.org/W2621280964","https://openalex.org/W2775183669","https://openalex.org/W4249836418","https://openalex.org/W6681648988","https://openalex.org/W7018266213"],"related_works":["https://openalex.org/W2479400771","https://openalex.org/W3127553152","https://openalex.org/W3002459461","https://openalex.org/W3173165160","https://openalex.org/W303883253","https://openalex.org/W3127649977","https://openalex.org/W4287331153","https://openalex.org/W2914403195","https://openalex.org/W4224015079","https://openalex.org/W2810872891"],"abstract_inverted_index":{"With":[0],"the":[1,10,37,116],"increasing":[2],"levels":[3],"of":[4,27,49,63,84],"access":[5],"to":[6,21,24,36,108],"higher":[7],"education":[8],"in":[9,70],"United":[11],"Kingdom,":[12],"larger":[13],"class":[14],"sizes":[15],"make":[16],"it":[17],"unrealistic":[18],"for":[19,47,67],"tutors":[20],"be":[22],"expected":[23],"identify":[25],"instances":[26],"peer-to-peer":[28],"plagiarism":[29,64,111,127],"by":[30,123],"eye":[31],"and":[32,56,75,93],"so":[33],"automated":[34],"solutions":[35],"problem":[38],"are":[39],"required.":[40],"This":[41],"document":[42],"details":[43],"a":[44,53,61],"novel":[45],"algorithm":[46,81,103],"comparison":[48,124],"suspect":[50],"documents":[51,74],"at":[52,115],"sentence":[54],"level":[55],"has":[57,104,120],"been":[58,106,121],"implemented":[59,102],"as":[60,89,96,98],"component":[62],"detection":[65,128],"software":[66,119],"detecting":[68,85],"similarities":[69],"both":[71],"natural":[72],"language":[73],"comments":[76],"within":[77],"program":[78],"source-code.":[79],"The":[80,101,118],"is":[82],"capable":[83],"sophisticated":[86],"obfuscation":[87],"(such":[88],"paraphrasing,":[90],"reordering,":[91],"merging,":[92],"splitting":[94],"sentences)":[95],"well":[97],"direct":[99],"copying.":[100],"also":[105],"used":[107],"successfully":[109],"detect":[110],"on":[112],"real":[113],"assignments":[114],"university.":[117],"evaluated":[122],"with":[125],"other":[126],"tools.":[129]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
