{"id":"https://openalex.org/W7204753262","doi":"https://doi.org/10.59562/metrik.v23i3.14414","title":"Development and Evaluation of an Indonesian Thesis-Title Similarity Detection System Using Hybrid TF-IDF\u2013SBERT Retrieval and LightGBM Reranking","display_name":"Development and Evaluation of an Indonesian Thesis-Title Similarity Detection System Using Hybrid TF-IDF\u2013SBERT Retrieval and LightGBM Reranking","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7204753262","doi":"https://doi.org/10.59562/metrik.v23i3.14414"},"language":"en","primary_location":{"id":"doi:10.59562/metrik.v23i3.14414","doi":"https://doi.org/10.59562/metrik.v23i3.14414","is_oa":true,"landing_page_url":"https://doi.org/10.59562/metrik.v23i3.14414","pdf_url":"https://journal.unm.ac.id/index.php/mediaelektrik/article/download/14414/8821","source":{"id":"https://openalex.org/S4210230011","display_name":"Jurnal Media Elektrik","issn_l":"1907-1728","issn":["1907-1728","2721-9100"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310315207","host_organization_name":"State University of Makassar","host_organization_lineage":["https://openalex.org/P4310315207"],"host_organization_lineage_names":["State University of Makassar"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Jurnal Media Elektrik","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://journal.unm.ac.id/index.php/mediaelektrik/article/download/14414/8821","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092858123","display_name":"Abdul Ma\u2019arief Al Imran","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405274958","display_name":"Institut Teknologi Sains dan Bisnis Muhammadiyah Selayar","ror":"https://ror.org/02pn0ed47","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405274958"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Abdul Ma'arief Al Imran","raw_affiliation_strings":["Institut Teknologi Sains dan Bisnis Muhammadiyah Selayar, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Teknologi Sains dan Bisnis Muhammadiyah Selayar, Indonesia","institution_ids":["https://openalex.org/I4405274958"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089457447","display_name":"Mursyid Ardiansyah","orcid":"https://orcid.org/0000-0002-5121-4450","observed_orcids":["https://orcid.org/0000-0002-5121-4450"]},"institutions":[{"id":"https://openalex.org/I4405274958","display_name":"Institut Teknologi Sains dan Bisnis Muhammadiyah Selayar","ror":"https://ror.org/02pn0ed47","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405274958"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Mursyid Ardiansyah","raw_affiliation_strings":["Institut Teknologi Sains dan Bisnis Muhammadiyah Selayar, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Teknologi Sains dan Bisnis Muhammadiyah Selayar, Indonesia","institution_ids":["https://openalex.org/I4405274958"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5117366661","display_name":"Ali Asgar Zainal Abidin","orcid":"https://orcid.org/0009-0006-2085-6545","observed_orcids":["https://orcid.org/0009-0006-2085-6545"]},"institutions":[{"id":"https://openalex.org/I4405274958","display_name":"Institut Teknologi Sains dan Bisnis Muhammadiyah Selayar","ror":"https://ror.org/02pn0ed47","country_code":"ID","type":"education","lineage":["https://openalex.org/I4405274958"]}],"countries":["ID"],"is_corresponding":false,"raw_author_name":"Ali Asgar Zainal Abidin","raw_affiliation_strings":["Institut Teknologi Sains dan Bisnis Muhammadiyah Selayar, Indonesia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut Teknologi Sains dan Bisnis Muhammadiyah Selayar, Indonesia","institution_ids":["https://openalex.org/I4405274958"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405274958"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.62798933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"23","issue":"3","first_page":"357","last_page":"386"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.5034000277519226,"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":0.5034000277519226,"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":0.19589999318122864,"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":0.1185000017285347,"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/indonesian-language","display_name":"Indonesian language","score":0.47099998593330383},{"id":"https://openalex.org/keywords/hybrid-search","display_name":"hybrid retrieval","score":0.6309999823570251},{"id":"https://openalex.org/keywords/xgboost","display_name":"XGBoost","score":0.6480000019073486},{"id":"https://openalex.org/keywords/pseudo-labeling","display_name":"pseudo-labeling","score":0.6930000185966492},{"id":"https://openalex.org/keywords/institutional-repositories","display_name":"institutional repositories","score":0.5759999752044678},{"id":"https://openalex.org/keywords/academic-integrity","display_name":"academic integrity","score":0.38600000739097595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.628000020980835},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5927000045776367},{"id":"https://openalex.org/C170130773","wikidata":"https://www.wikidata.org/wiki/Q216378","display_name":"Usability","level":2,"score":0.512499988079071},{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.5091000199317932},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45879998803138733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4050999879837036},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39559999108314514},{"id":"https://openalex.org/C163864269","wikidata":"https://www.wikidata.org/wiki/Q1107106","display_name":"Cohen's kappa","level":2,"score":0.3871999979019165},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3702999949455261},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.35120001435279846},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.30169999599456787},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.59562/metrik.v23i3.14414","doi":"https://doi.org/10.59562/metrik.v23i3.14414","is_oa":true,"landing_page_url":"https://doi.org/10.59562/metrik.v23i3.14414","pdf_url":"https://journal.unm.ac.id/index.php/mediaelektrik/article/download/14414/8821","source":{"id":"https://openalex.org/S4210230011","display_name":"Jurnal Media Elektrik","issn_l":"1907-1728","issn":["1907-1728","2721-9100"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310315207","host_organization_name":"State University of Makassar","host_organization_lineage":["https://openalex.org/P4310315207"],"host_organization_lineage_names":["State University of Makassar"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Jurnal Media Elektrik","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.59562/metrik.v23i3.14414","doi":"https://doi.org/10.59562/metrik.v23i3.14414","is_oa":true,"landing_page_url":"https://doi.org/10.59562/metrik.v23i3.14414","pdf_url":"https://journal.unm.ac.id/index.php/mediaelektrik/article/download/14414/8821","source":{"id":"https://openalex.org/S4210230011","display_name":"Jurnal Media Elektrik","issn_l":"1907-1728","issn":["1907-1728","2721-9100"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310315207","host_organization_name":"State University of Makassar","host_organization_lineage":["https://openalex.org/P4310315207"],"host_organization_lineage_names":["State University of Makassar"],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Jurnal Media Elektrik","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204753262.pdf","grobid_xml":"https://content.openalex.org/works/W7204753262.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7154130265","https://openalex.org/W7213948067","https://openalex.org/W4416377259","https://openalex.org/W7155632534","https://openalex.org/W7167628298","https://openalex.org/W7215891843","https://openalex.org/W7219397337","https://openalex.org/W4413210320","https://openalex.org/W7222845054","https://openalex.org/W3214007109"],"abstract_inverted_index":{"This":[0],"study":[1],"developed":[2],"and":[3,50,57,112,137,176],"evaluated":[4,70],"an":[5,72,108,127],"Indonesian":[6],"thesis-title":[7],"similarity":[8],"detection":[9],"system":[10,38,158],"to":[11],"support":[12,160],"the":[13,65,104,142,147,170],"early":[14],"screening":[15],"of":[16,25,84,100,110,116,133,172],"potentially":[17],"similar":[18],"research":[19],"titles.":[20],"The":[21,37,157],"reference":[22],"corpus":[23,175],"consisted":[24],"28,117":[26],"unique":[27],"thesis":[28],"titles":[29],"collected":[30],"from":[31,77],"a":[32,78,97,113,122,173],"publicly":[33],"accessible":[34],"institutional":[35],"repository.":[36],"integrates":[39],"TF-IDF-based":[40],"lexical":[41],"retrieval,":[42,45],"SBERT-based":[43],"semantic":[44],"Union":[46],"Top-K":[47],"candidate":[48,86],"selection,":[49],"machine":[51],"learning":[52],"reranking.":[53],"Logistic":[54],"Regression,":[55],"XGBoost,":[56],"LightGBM":[58,102],"were":[59,89],"trained":[60],"using":[61],"threshold-derived":[62],"pseudo-labels,":[63],"while":[64,141],"final":[66],"model":[67],"performance":[68,131],"was":[69],"on":[71,135,139],"independent":[73],"human-validated":[74],"dataset":[75],"constructed":[76],"title-disjoint":[79],"evaluation":[80,120],"partition.":[81],"A":[82],"total":[83],"900":[85],"title":[87],"pairs":[88],"independently":[90],"assessed":[91],"by":[92,169],"two":[93,154],"academic":[94,161],"validators,":[95],"achieving":[96],"Cohen\u2019s":[98],"kappa":[99],"0.877.":[101],"achieved":[103],"best":[105],"performance,":[106],"with":[107,153],"accuracy":[109],"94.67%":[111],"macro":[114],"F1-score":[115],"0.9467.":[117],"ISO/IEC":[118],"25010":[119],"showed":[121],"100%":[123],"functional":[124],"pass":[125],"rate,":[126],"84.17%":[128],"usability":[129],"score,":[130],"scores":[132],"92.3%":[134],"mobile":[136],"96.8%":[138],"desktop,":[140],"automated":[143],"security":[144],"assessment":[145],"categorized":[146],"staging":[148],"deployment":[149],"as":[150],"Fairly":[151],"Secure":[152],"medium-risk":[155],"findings.":[156],"can":[159],"title-similarity":[162],"screening;":[163],"however,":[164],"its":[165],"generalizability":[166],"remains":[167],"limited":[168],"use":[171],"single-institution":[174],"requires":[177],"further":[178],"multi-institutional":[179],"validation.":[180]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-01T00:00:00"}