{"id":"https://openalex.org/W4390549901","doi":"https://doi.org/10.1109/sita60746.2023.10373698","title":"Identifying Near-Duplicate Pairs in Exams: Similarity Detection Using Kshingling, Minhashing, and LSH","display_name":"Identifying Near-Duplicate Pairs in Exams: Similarity Detection Using Kshingling, Minhashing, and LSH","publication_year":2023,"publication_date":"2023-11-22","ids":{"openalex":"https://openalex.org/W4390549901","doi":"https://doi.org/10.1109/sita60746.2023.10373698"},"language":"en","primary_location":{"id":"doi:10.1109/sita60746.2023.10373698","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/sita60746.2023.10373698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Intelligent Systems: Theories and Applications (SITA)","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/A5093646985","display_name":"El Rhezzali Nabila","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149368","display_name":"\u00c9cole des Sciences de I'information","ror":"https://ror.org/04wx25x02","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210149368"]},{"id":"https://openalex.org/I4210154402","display_name":"Institut Sup\u00e9rieur de l'Information et de la Communication","ror":"https://ror.org/05awwc719","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210154402"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"El Rhezzali Nabila","raw_affiliation_strings":["Information Sciences School,ITQAN Team, LyRica Lab,Rabat,Morocco","ITQAN Team, LyRica Lab, Information Sciences School, Rabat, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences School,ITQAN Team, LyRica Lab,Rabat,Morocco","institution_ids":["https://openalex.org/I4210154402"]},{"raw_affiliation_string":"ITQAN Team, LyRica Lab, Information Sciences School, Rabat, Morocco","institution_ids":["https://openalex.org/I4210149368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022174584","display_name":"Imane Hilal","orcid":"https://orcid.org/0000-0002-0082-5438"},"institutions":[{"id":"https://openalex.org/I4210149368","display_name":"\u00c9cole des Sciences de I'information","ror":"https://ror.org/04wx25x02","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210149368"]},{"id":"https://openalex.org/I4210154402","display_name":"Institut Sup\u00e9rieur de l'Information et de la Communication","ror":"https://ror.org/05awwc719","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210154402"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Hilal Imane","raw_affiliation_strings":["Information Sciences School,ITQAN Team, LyRica Lab,Rabat,Morocco","ITQAN Team, LyRica Lab, Information Sciences School, Rabat, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences School,ITQAN Team, LyRica Lab,Rabat,Morocco","institution_ids":["https://openalex.org/I4210154402"]},{"raw_affiliation_string":"ITQAN Team, LyRica Lab, Information Sciences School, Rabat, Morocco","institution_ids":["https://openalex.org/I4210149368"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070492378","display_name":"Hnida Meriem","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149368","display_name":"\u00c9cole des Sciences de I'information","ror":"https://ror.org/04wx25x02","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210149368"]},{"id":"https://openalex.org/I4210154402","display_name":"Institut Sup\u00e9rieur de l'Information et de la Communication","ror":"https://ror.org/05awwc719","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210154402"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Hnida Meriem","raw_affiliation_strings":["Information Sciences School,ITQAN Team, LyRica Lab,Rabat,Morocco","ITQAN Team, LyRica Lab, Information Sciences School, Rabat, Morocco"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences School,ITQAN Team, LyRica Lab,Rabat,Morocco","institution_ids":["https://openalex.org/I4210154402"]},{"raw_affiliation_string":"ITQAN Team, LyRica Lab, Information Sciences School, Rabat, Morocco","institution_ids":["https://openalex.org/I4210149368"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1586,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56674279,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9987000226974487,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9987000226974487,"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":0.9975000023841858,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9660999774932861,"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":0.7764667272567749},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.7544587850570679},{"id":"https://openalex.org/keywords/cheating","display_name":"Cheating","score":0.6478410959243774},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5840397477149963},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.5811563730239868},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5677236318588257},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.49533477425575256},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4590297043323517},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4269946217536926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39461690187454224},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3883362114429474},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3411213159561157},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.20445001125335693},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.09661102294921875},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.07704043388366699}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764667272567749},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.7544587850570679},{"id":"https://openalex.org/C2778024590","wikidata":"https://www.wikidata.org/wiki/Q2357432","display_name":"Cheating","level":2,"score":0.6478410959243774},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5840397477149963},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.5811563730239868},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5677236318588257},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.49533477425575256},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4590297043323517},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4269946217536926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39461690187454224},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3883362114429474},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3411213159561157},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.20445001125335693},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.09661102294921875},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.07704043388366699},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sita60746.2023.10373698","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/sita60746.2023.10373698","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 14th International Conference on Intelligent Systems: Theories and Applications (SITA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1673518641","https://openalex.org/W1736726159","https://openalex.org/W1981617416","https://openalex.org/W1995742667","https://openalex.org/W2010392031","https://openalex.org/W2034190452","https://openalex.org/W2045354220","https://openalex.org/W2048779798","https://openalex.org/W2081193615","https://openalex.org/W2091856951","https://openalex.org/W2111192396","https://openalex.org/W2132069633","https://openalex.org/W2145065594","https://openalex.org/W2148885851","https://openalex.org/W2171313960","https://openalex.org/W2197479404","https://openalex.org/W2524168323","https://openalex.org/W2610332593","https://openalex.org/W2769241325","https://openalex.org/W2994985738","https://openalex.org/W6601696544","https://openalex.org/W6629956336","https://openalex.org/W6633661181","https://openalex.org/W7043235420"],"related_works":["https://openalex.org/W2012288173","https://openalex.org/W1968538666","https://openalex.org/W2097662580","https://openalex.org/W2000601968","https://openalex.org/W2144265691","https://openalex.org/W1971922616","https://openalex.org/W3145472249","https://openalex.org/W2033383639","https://openalex.org/W3108918257","https://openalex.org/W3016124764"],"abstract_inverted_index":{"In":[0],"the":[1,36,43,72,84],"field":[2],"of":[3,74],"data":[4],"mining,":[5],"identifying":[6],"near-duplicate":[7,64],"documents":[8],"is":[9],"a":[10,54],"key":[11],"challenge.":[12],"This":[13,51],"task,":[14],"crucial":[15],"for":[16],"detecting":[17],"cheating":[18],"in":[19,66,78],"online":[20,67],"exams,":[21],"can":[22],"be":[23],"approached":[24],"using":[25,35],"techniques":[26],"from":[27],"Natural":[28],"Language":[29],"Processing:":[30],"Shingling":[31],"and":[32],"Minhashing.":[33],"Furthermore,":[34],"Locality":[37],"Similarity":[38],"Hashing":[39],"(LSH)":[40],"approach":[41,77],"refines":[42],"process":[44],"by":[45],"focusing":[46],"on":[47],"high-probability":[48],"document":[49],"comparisons.":[50],"paper":[52],"introduces":[53],"novel":[55],"method":[56],"that":[57],"combines":[58],"K-shingling,":[59],"Minhashing,":[60],"LSH,":[61],"to":[62,86],"uncover":[63],"pairs":[65],"exams.":[68],"Experimental":[69],"results":[70],"highlight":[71],"success":[73],"this":[75],"integrated":[76],"enhancing":[79],"detection":[80],"accuracy,":[81],"ultimately":[82],"strengthening":[83],"capability":[85],"address":[87],"academic":[88],"dishonesty.":[89]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}
