{"id":"https://openalex.org/W2513715602","doi":"https://doi.org/10.1145/2905055.2905267","title":"A Framework for Detecting External Plagiarism from Monolingual Documents","display_name":"A Framework for Detecting External Plagiarism from Monolingual Documents","publication_year":2016,"publication_date":"2016-03-04","ids":{"openalex":"https://openalex.org/W2513715602","doi":"https://doi.org/10.1145/2905055.2905267","mag":"2513715602"},"language":"en","primary_location":{"id":"doi:10.1145/2905055.2905267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2905055.2905267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies","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/A5076323107","display_name":"Ritambhra Korpal","orcid":null},"institutions":[{"id":"https://openalex.org/I878213199","display_name":"Savitribai Phule Pune University","ror":"https://ror.org/044g6d731","country_code":"IN","type":"education","lineage":["https://openalex.org/I878213199"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Ritambhra Korpal","raw_affiliation_strings":["University of Pune, India"],"affiliations":[{"raw_affiliation_string":"University of Pune, India","institution_ids":["https://openalex.org/I878213199"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016463217","display_name":"Saugata Bose","orcid":null},"institutions":[{"id":"https://openalex.org/I3131708325","display_name":"University of Liberal Arts Bangladesh","ror":"https://ror.org/012br3z79","country_code":"BD","type":"education","lineage":["https://openalex.org/I3131708325"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Saugata Bose","raw_affiliation_strings":["University of Liberal Arts Bangladesh"],"affiliations":[{"raw_affiliation_string":"University of Liberal Arts Bangladesh","institution_ids":["https://openalex.org/I3131708325"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076323107"],"corresponding_institution_ids":["https://openalex.org/I878213199"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.05173739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"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/T10028","display_name":"Topic Modeling","score":0.9973000288009644,"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/T11492","display_name":"Academic integrity and plagiarism","score":0.9968000054359436,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9890000224113464,"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":0.8108031749725342},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.7023492455482483},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.6948984265327454},{"id":"https://openalex.org/keywords/confusion-matrix","display_name":"Confusion matrix","score":0.6735935211181641},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.629021167755127},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.5905239582061768},{"id":"https://openalex.org/keywords/confusion","display_name":"Confusion","score":0.5556403398513794},{"id":"https://openalex.org/keywords/false-positives-and-false-negatives","display_name":"False positives and false negatives","score":0.5324780941009521},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.5170748829841614},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.513450026512146},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.49431586265563965},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3839320242404938},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33635109663009644},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13923993706703186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8108031749725342},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.7023492455482483},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.6948984265327454},{"id":"https://openalex.org/C138602881","wikidata":"https://www.wikidata.org/wiki/Q2709591","display_name":"Confusion matrix","level":2,"score":0.6735935211181641},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.629021167755127},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.5905239582061768},{"id":"https://openalex.org/C2781140086","wikidata":"https://www.wikidata.org/wiki/Q557945","display_name":"Confusion","level":2,"score":0.5556403398513794},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.5324780941009521},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.5170748829841614},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.513450026512146},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.49431586265563965},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3839320242404938},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33635109663009644},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13923993706703186},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C11171543","wikidata":"https://www.wikidata.org/wiki/Q41630","display_name":"Psychoanalysis","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2905055.2905267","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2905055.2905267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8799999952316284}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1562017034","https://openalex.org/W1566018662","https://openalex.org/W1589844230","https://openalex.org/W1660390307","https://openalex.org/W1679197109","https://openalex.org/W1967925097","https://openalex.org/W1986266715","https://openalex.org/W2025595753","https://openalex.org/W2064874120","https://openalex.org/W2101105183","https://openalex.org/W2112890327","https://openalex.org/W2115269749","https://openalex.org/W2121135610","https://openalex.org/W2149182189","https://openalex.org/W2165022036","https://openalex.org/W2282803707","https://openalex.org/W2992973762","https://openalex.org/W3105439152"],"related_works":["https://openalex.org/W1557094818","https://openalex.org/W2183246718","https://openalex.org/W1973412793","https://openalex.org/W2099261052","https://openalex.org/W4292605373","https://openalex.org/W2951146195","https://openalex.org/W4226316650","https://openalex.org/W3123215897","https://openalex.org/W2153600354","https://openalex.org/W4366202965"],"abstract_inverted_index":{"The":[0,96],"internet":[1],"has":[2,88,117,131],"increased":[3],"the":[4,62,82,93,109,136,149],"copy-paste":[5],"scenarios":[6],"amongst":[7,12],"students":[8],"as":[9,11,47,49],"well":[10,48],"researchers":[13],"leading":[14],"to":[15,57,67,91,120,134,147],"different":[16],"levels":[17,140],"of":[18,25,141,164],"plagiarized":[19,59],"documents.":[20],"For":[21,79],"this":[22,35],"reason,":[23],"much":[24],"research":[26],"is":[27,39,65,98],"focused":[28],"on":[29,66,100],"for":[30],"detecting":[31,81],"plagiarism":[32,74,156],"automatically.":[33],"In":[34],"paper,":[36],"an":[37],"initiative":[38],"discussed":[40],"where":[41],"Natural":[42],"Language":[43],"Processing":[44],"(NLP)":[45],"techniques,":[46],"supervised":[50,127],"machine":[51],"learning":[52,129],"algorithms":[53],"have":[54,104],"been":[55,89,105,118,132],"combined":[56],"detect":[58],"texts.":[60],"Here,":[61],"major":[63],"emphasis":[64],"construct":[68,92],"a":[69,159],"framework":[70,97,157],"which":[71,103],"detects":[72],"external":[73],"from":[75],"monolingual":[76],"texts":[77],"successfully.":[78],"successfully":[80],"plagiarism,":[83],"n-gram":[84],"frequency":[85],"comparison":[86],"approach":[87],"implemented":[90],"model":[94],"framework.":[95],"based":[99],"120":[101],"characteristics":[102,124],"extracted":[106],"during":[107],"pre-processing":[108],"documents":[110,137],"using":[111],"NLP":[112],"approach.":[113],"Afterwards,":[114],"filter":[115],"metrics":[116],"applied":[119],"select":[121],"most":[122],"relevant":[123],"and":[125,152,170],"then":[126],"classification":[128],"algorithm":[130],"used":[133],"classify":[135],"in":[138],"four":[139],"plagiarism.":[142],"Confusion":[143],"matrix":[144],"was":[145],"built":[146],"estimate":[148],"false":[150,153,168,171],"positives":[151],"negatives.":[154],"Our":[155],"achieved":[158],"very":[160],"high":[161],"accuracy":[162],"score":[163],"89%":[165],"with":[166],"low":[167],"positive":[169],"negative":[172],"rate.":[173]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}