{"id":"https://openalex.org/W2069644548","doi":"https://doi.org/10.1109/his.2012.6421362","title":"Plagiarism detection in text using Vector Space Model","display_name":"Plagiarism detection in text using Vector Space Model","publication_year":2012,"publication_date":"2012-12-01","ids":{"openalex":"https://openalex.org/W2069644548","doi":"https://doi.org/10.1109/his.2012.6421362","mag":"2069644548"},"language":"en","primary_location":{"id":"doi:10.1109/his.2012.6421362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/his.2012.6421362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th International Conference on Hybrid Intelligent Systems (HIS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085370631","display_name":"Asif Ekbal","orcid":"https://orcid.org/0000-0003-3612-8834"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Asif Ekbal","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology, Patna, Patna, India","Department of Computer Science and Engineering, Indian Institute of Technology Patna, India-800 013"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, India-800 013","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025979359","display_name":"Sriparna Saha","orcid":"https://orcid.org/0000-0001-5494-9391"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriparna Saha","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology, Patna, Patna, India","Department of Computer Science and Engineering, Indian Institute of Technology Patna, India-800 013"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, India-800 013","institution_ids":["https://openalex.org/I132153292"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042988035","display_name":"Gaurav Choudhary","orcid":"https://orcid.org/0000-0003-3378-2945"},"institutions":[{"id":"https://openalex.org/I132153292","display_name":"Indian Institute of Technology Patna","ror":"https://ror.org/01ft5vz71","country_code":"IN","type":"education","lineage":["https://openalex.org/I132153292"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Gaurav Choudhary","raw_affiliation_strings":["Department of Computer Science and Engineering, Indian Institute of Technology, Patna, Patna, India","Department of Computer Science and Engineering, Indian Institute of Technology Patna, India-800 013"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology, Patna, Patna, India","institution_ids":["https://openalex.org/I132153292"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Indian Institute of Technology Patna, India-800 013","institution_ids":["https://openalex.org/I132153292"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I132153292"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"366","last_page":"371"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9969000220298767,"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":0.9969000220298767,"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/T10028","display_name":"Topic Modeling","score":0.9919000267982483,"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/T10260","display_name":"Software Engineering Research","score":0.9848999977111816,"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":0.7897800207138062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7783883810043335},{"id":"https://openalex.org/keywords/copying","display_name":"Copying","score":0.7645457983016968},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6321706175804138},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5441100001335144},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5425854325294495},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5251566767692566},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.521317183971405},{"id":"https://openalex.org/keywords/magic","display_name":"MAGIC (telescope)","score":0.500335693359375},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.49048563838005066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47363629937171936},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4704510271549225},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42635053396224976},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1111859679222107}],"concepts":[{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.7897800207138062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7783883810043335},{"id":"https://openalex.org/C2779151265","wikidata":"https://www.wikidata.org/wiki/Q1156791","display_name":"Copying","level":2,"score":0.7645457983016968},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6321706175804138},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5441100001335144},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5425854325294495},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5251566767692566},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.521317183971405},{"id":"https://openalex.org/C2777704519","wikidata":"https://www.wikidata.org/wiki/Q45732","display_name":"MAGIC (telescope)","level":2,"score":0.500335693359375},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.49048563838005066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47363629937171936},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4704510271549225},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42635053396224976},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1111859679222107},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/his.2012.6421362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/his.2012.6421362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 12th International Conference on Hybrid Intelligent Systems (HIS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W54772338","https://openalex.org/W184453455","https://openalex.org/W343431744","https://openalex.org/W1480177570","https://openalex.org/W1509629370","https://openalex.org/W1544505227","https://openalex.org/W1564629710","https://openalex.org/W1974930421","https://openalex.org/W2108378253","https://openalex.org/W2143296909","https://openalex.org/W2164634022","https://openalex.org/W6602218007","https://openalex.org/W6607442393","https://openalex.org/W6611624874","https://openalex.org/W6630489051","https://openalex.org/W6632555176","https://openalex.org/W6633717541"],"related_works":["https://openalex.org/W4308771405","https://openalex.org/W2355873265","https://openalex.org/W2963669501","https://openalex.org/W2010433882","https://openalex.org/W3165641622","https://openalex.org/W147509096","https://openalex.org/W2186084918","https://openalex.org/W3154880776","https://openalex.org/W2313765556","https://openalex.org/W2893658681"],"abstract_inverted_index":{"Plagiarism":[0,17],"denotes":[1],"the":[2,20,24,45,51,67,75,108,115,129,135,153,166,176,187,198,212],"act":[3],"of":[4,26,77,79,110,125,160,168],"copying":[5],"someone":[6],"else's":[7],"idea":[8],"(or,":[9],"works)":[10],"and":[11,73,148,204],"claiming":[12],"it":[13],"as":[14],"his/her":[15],"own.":[16],"detection":[18],"is":[19,118],"procedure":[21],"to":[22,44,106,137,195],"detect":[23],"texts":[25],"a":[27,82,89,100,158,192],"given":[28,101],"document":[29,103,117,203],"which":[30,114],"are":[31,42],"plagiarized,":[32],"i.e.":[33],"copied":[34,52],"from":[35,36,113],"some":[37],"other":[38],"documents.":[39,207],"Potential":[40],"challenges":[41],"due":[43],"facts":[46],"that":[47,162],"plagiarists":[48],"often":[49],"obfuscate":[50],"texts;":[53],"might":[54,64],"shuffle,":[55],"remove,":[56],"insert,":[57],"or":[58,61],"replace":[59],"words":[60,70,80],"short":[62],"phrases;":[63],"also":[65],"restructure":[66],"sentences":[68],"replacing":[69],"with":[71],"synonyms;":[72],"changing":[74],"order":[76],"appearances":[78],"in":[81,201],"sentence.":[83],"In":[84,128,152,186],"this":[85,183],"paper":[86],"we":[87,104,122,132,156,190,209],"propose":[88,123],"technique":[90],"based":[91,174],"on":[92,175],"textual":[93],"similarity":[94],"for":[95,182],"external":[96],"plagiarism":[97],"detection.":[98],"For":[99],"suspicious":[102,116,202],"have":[105],"identify":[107],"set":[109],"source":[111,206],"documents":[112,136,161],"copied.":[119],"The":[120],"method":[121],"comprises":[124],"four":[126],"phases.":[127],"first":[130],"phase,":[131],"process":[133],"all":[134],"generate":[138],"tokens,":[139],"lemmas,":[140],"finding":[141],"Part-of-Speech":[142],"(PoS)":[143],"classes,":[144],"character-offsets,":[145],"sentence":[146],"numbers":[147],"named-entity":[149],"(NE)":[150],"classes.":[151],"second":[154],"phase":[155,189],"select":[157],"subset":[159],"may":[163],"possibly":[164],"be":[165],"sources":[167],"plagiarism.":[169],"We":[170],"use":[171,191],"an":[172],"approach":[173,194],"traditional":[177],"Vector":[178],"Space":[179],"Model":[180],"(VSM)":[181],"candidate":[184],"selection.":[185],"third":[188],"graph-based":[193],"find":[196],"out":[197,211],"similar":[199],"passages":[200],"selected":[205],"Finally":[208],"filter":[210],"false":[213],"detections":[214],"<sup":[215],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[216],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[217],".":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}