{"id":"https://openalex.org/W4416396346","doi":"https://doi.org/10.1051/e3sconf/202566401004","title":"The context similarity problem in academic plagiarism detection: A case study on differentiating originality from collusion in a homogeneous dataset","display_name":"The context similarity problem in academic plagiarism detection: A case study on differentiating originality from collusion in a homogeneous dataset","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416396346","doi":"https://doi.org/10.1051/e3sconf/202566401004"},"language":"en","primary_location":{"id":"doi:10.1051/e3sconf/202566401004","doi":"https://doi.org/10.1051/e3sconf/202566401004","is_oa":true,"landing_page_url":"https://doi.org/10.1051/e3sconf/202566401004","pdf_url":"https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/64/e3sconf_issat2025_01004.pdf","source":{"id":"https://openalex.org/S4210186093","display_name":"E3S Web of Conferences","issn_l":"2267-1242","issn":["2267-1242","2555-0403"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["ddh","doaj","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319748","host_organization_name":"EDP Sciences","host_organization_lineage":["https://openalex.org/P4310319748","https://openalex.org/P4310319982"],"host_organization_lineage_names":["EDP Sciences","Science Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"E3S Web of Conferences","raw_type":"journal-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/64/e3sconf_issat2025_01004.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076193984","display_name":"Djoko Cahyo Utomo Lieharyani","orcid":"https://orcid.org/0000-0003-2573-5778","observed_orcids":["https://orcid.org/0000-0003-2573-5778"]},"institutions":[{"id":"https://openalex.org/I4400008984","display_name":"Politeknik Negeri Bandung","ror":"https://ror.org/05v5br676","country_code":"ID","type":"education","lineage":["https://openalex.org/I4400008984"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Djoko Cahyo Utomo Lieharyani","raw_affiliation_strings":["Department of Informatics Engineering, Politeknik Negeri Bandung"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics Engineering, Politeknik Negeri Bandung","institution_ids":["https://openalex.org/I4400008984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112683520","display_name":"Jonner Hutahaean","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4400008984","display_name":"Politeknik Negeri Bandung","ror":"https://ror.org/05v5br676","country_code":"ID","type":"education","lineage":["https://openalex.org/I4400008984"]}],"countries":["ID"],"is_corresponding":true,"raw_author_name":"Jonner Hutahaean","raw_affiliation_strings":["Department of Informatics Engineering, Politeknik Negeri Bandung"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics Engineering, Politeknik Negeri Bandung","institution_ids":["https://openalex.org/I4400008984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087447920","display_name":"Ade Chandra Nugraha","orcid":"https://orcid.org/0000-0002-6955-2079","observed_orcids":["https://orcid.org/0000-0002-6955-2079"]},"institutions":[{"id":"https://openalex.org/I4400008984","display_name":"Politeknik Negeri Bandung","ror":"https://ror.org/05v5br676","country_code":"ID","type":"education","lineage":["https://openalex.org/I4400008984"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ade Chandra Nugraha","raw_affiliation_strings":["Department of Informatics Engineering, Politeknik Negeri Bandung"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics Engineering, Politeknik Negeri Bandung","institution_ids":["https://openalex.org/I4400008984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074577497","display_name":"Suprihanto Suprihanto","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4400008984","display_name":"Politeknik Negeri Bandung","ror":"https://ror.org/05v5br676","country_code":"ID","type":"education","lineage":["https://openalex.org/I4400008984"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Suprihanto","raw_affiliation_strings":["Department of Informatics Engineering, Politeknik Negeri Bandung"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics Engineering, Politeknik Negeri Bandung","institution_ids":["https://openalex.org/I4400008984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009998985","display_name":"Didik Suwito Pribadi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4400008984","display_name":"Politeknik Negeri Bandung","ror":"https://ror.org/05v5br676","country_code":"ID","type":"education","lineage":["https://openalex.org/I4400008984"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Didik Suwito Pribadi","raw_affiliation_strings":["Department of Informatics Engineering, Politeknik Negeri Bandung"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics Engineering, Politeknik Negeri Bandung","institution_ids":["https://openalex.org/I4400008984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5112683520"],"corresponding_institution_ids":["https://openalex.org/I4400008984"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35232252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"664","issue":null,"first_page":"01004","last_page":"01004"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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/T14414","display_name":"Artificial Intelligence in Education","score":9.999999747378752e-05,"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/sentence-bert","display_name":"Sentence-BERT","score":0.9129999876022339},{"id":"https://openalex.org/keywords/word-similarity","display_name":"word similarity","score":0.6840000152587891},{"id":"https://openalex.org/keywords/jaccard-similarity","display_name":"Jaccard similarity","score":0.9760000109672546},{"id":"https://openalex.org/keywords/false-positive-results","display_name":"false positives","score":0.597000002861023},{"id":"https://openalex.org/keywords/academic-integrity","display_name":"academic integrity","score":0.9679999947547913}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6901000142097473},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6430000066757202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5383999943733215},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5060999989509583},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.49050000309944153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48030000925064087},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.47510001063346863},{"id":"https://openalex.org/C2776950860","wikidata":"https://www.wikidata.org/wiki/Q2914681","display_name":"Originality","level":3,"score":0.4634000062942505},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.461899995803833},{"id":"https://openalex.org/C2781198186","wikidata":"https://www.wikidata.org/wiki/Q701521","display_name":"Collusion","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3668000102043152},{"id":"https://openalex.org/C2777515626","wikidata":"https://www.wikidata.org/wiki/Q496939","display_name":"Levenshtein distance","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C143271835","wikidata":"https://www.wikidata.org/wiki/Q254515","display_name":"Similitude","level":2,"score":0.3034000098705292},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2854999899864197},{"id":"https://openalex.org/C98954769","wikidata":"https://www.wikidata.org/wiki/Q1759657","display_name":"Lexical semantics","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C126706616","wikidata":"https://www.wikidata.org/wiki/Q2944660","display_name":"Lexical item","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2662000060081482},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2581000030040741},{"id":"https://openalex.org/C76188268","wikidata":"https://www.wikidata.org/wiki/Q1783165","display_name":"Context effect","level":3,"score":0.257099986076355},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C198942812","wikidata":"https://www.wikidata.org/wiki/Q496618","display_name":"Semantic property","level":2,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1051/e3sconf/202566401004","doi":"https://doi.org/10.1051/e3sconf/202566401004","is_oa":true,"landing_page_url":"https://doi.org/10.1051/e3sconf/202566401004","pdf_url":"https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/64/e3sconf_issat2025_01004.pdf","source":{"id":"https://openalex.org/S4210186093","display_name":"E3S Web of Conferences","issn_l":"2267-1242","issn":["2267-1242","2555-0403"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["ddh","doaj","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319748","host_organization_name":"EDP Sciences","host_organization_lineage":["https://openalex.org/P4310319748","https://openalex.org/P4310319982"],"host_organization_lineage_names":["EDP Sciences","Science Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"E3S Web of Conferences","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:b75a4a3b668649b5b8eb2347b4f07a91","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/b75a4a3b668649b5b8eb2347b4f07a91","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"E3S Web of Conferences, Vol 664, p 01004 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1051/e3sconf/202566401004","doi":"https://doi.org/10.1051/e3sconf/202566401004","is_oa":true,"landing_page_url":"https://doi.org/10.1051/e3sconf/202566401004","pdf_url":"https://www.e3s-conferences.org/articles/e3sconf/pdf/2025/64/e3sconf_issat2025_01004.pdf","source":{"id":"https://openalex.org/S4210186093","display_name":"E3S Web of Conferences","issn_l":"2267-1242","issn":["2267-1242","2555-0403"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["ddh","doaj","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310319748","host_organization_name":"EDP Sciences","host_organization_lineage":["https://openalex.org/P4310319748","https://openalex.org/P4310319982"],"host_organization_lineage_names":["EDP Sciences","Science Press"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"E3S Web of Conferences","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6164000034332275,"display_name":"Quality education","id":"https://metadata.un.org/sdg/4"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416396346.pdf","grobid_xml":"https://content.openalex.org/works/W4416396346.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W3128465392","https://openalex.org/W3170952411","https://openalex.org/W3210610489","https://openalex.org/W4220969787","https://openalex.org/W4308516693","https://openalex.org/W4312394755","https://openalex.org/W4385662142","https://openalex.org/W4404733768","https://openalex.org/W4405839918"],"related_works":["https://openalex.org/W7213225172","https://openalex.org/W934772423","https://openalex.org/W2735162248","https://openalex.org/W2846426648","https://openalex.org/W2753312454","https://openalex.org/W4409273263","https://openalex.org/W7164124688","https://openalex.org/W4233687542","https://openalex.org/W7154513745","https://openalex.org/W2106667907"],"abstract_inverted_index":{"Intraclass":[0],"collusion":[1],"poses":[2],"a":[3,43,47,58,68,81,90,106,126,153,167],"significant":[4],"challenge":[5],"for":[6,120,159,169],"automated":[7],"detection":[8],"systems":[9],"within":[10],"homogeneous":[11],"datasets":[12],"from":[13],"e-learning":[14],"platforms,":[15],"where":[16],"legitimate":[17],"contextual":[18],"overlap":[19],"often":[20],"leads":[21],"to":[22],"high":[23,115],"false-positive":[24],"rates.":[25],"This":[26,37,123],"\u201ccontext":[27],"similarity":[28,116],"problem\u201d":[29],"questions":[30],"the":[31,96,102,132,160],"utility":[32],"of":[33,46,61,93,109,118,134,163],"advanced":[34],"semantic":[35,97,136],"models.":[36],"study":[38],"confronts":[39],"this":[40,139],"issue":[41],"through":[42],"quantitative":[44],"comparison":[45],"state-of-the-art":[48],"Sentence-BERT":[49],"model":[50,98],"against":[51],"traditional":[52],"lexical":[53,72,146],"methods":[54,73,147],"(Levenshtein,":[55],"Jaccard)":[56],"on":[57],"real-world":[59],"dataset":[60],"854":[62],"student":[63],"answers.":[64],"Our":[65],"findings":[66],"reveal":[67],"compelling,":[69],"counter-intuitive":[70],"result:":[71],"are":[74,148],"demonstrably":[75],"more":[76,154],"effective.":[77],"Levenshtein":[78],"Similarity":[79],"achieved":[80],"superior":[82],"F1-score":[83,108],"(0.74)":[84],"and":[85,111,156],"F2-score":[86],"(0.75),":[87],"underpinned":[88],"by":[89,101,129],"strong":[91],"recall":[92],"0.76.":[94],"Conversely,":[95],"was":[99],"confounded":[100],"dataset\u2019s":[103],"homogeneity,":[104],"yielding":[105],"modest":[107],"0.57":[110],"requiring":[112],"an":[113],"impractically":[114],"threshold":[117],"0.98":[119],"optimal":[121],"performance.":[122],"research":[124],"provides":[125],"critical":[127],"contribution":[128],"empirically":[130],"demonstrating":[131],"limitations":[133],"purely":[135],"approaches":[137],"in":[138,172],"specific":[140],"context.":[141],"We":[142],"conclude":[143],"that":[144],"well-established":[145],"not":[149],"obsolete":[150],"but":[151],"remain":[152],"reliable":[155],"practical":[157],"tool":[158],"initial":[161],"screening":[162],"academic":[164,174],"collusion,":[165],"suggesting":[166],"need":[168],"hybrid":[170],"strategies":[171],"modern":[173],"integrity":[175],"systems.":[176]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2025-11-20T00:00:00"}