{"id":"https://openalex.org/W7203974065","doi":"https://doi.org/10.1016/j.asoc.2026.116272","title":"Ghost Rate: A pre-training geometric quality diagnostic for synthetic oversampling in imbalanced text classification","display_name":"Ghost Rate: A pre-training geometric quality diagnostic for synthetic oversampling in imbalanced text classification","publication_year":2026,"publication_date":"2026-08-22","ids":{"openalex":"https://openalex.org/W7203974065","doi":"https://doi.org/10.1016/j.asoc.2026.116272"},"language":"en","primary_location":{"id":"doi:10.1016/j.asoc.2026.116272","doi":"https://doi.org/10.1016/j.asoc.2026.116272","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.asoc.2026.116272","pdf_url":null,"source":{"id":"https://openalex.org/S140556538","display_name":"Applied Soft Computing","issn_l":"1568-4946","issn":["1568-4946","1872-9681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","jufo-1","ki-jl-1","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Soft Computing","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"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/A5017101202","display_name":"Marwa Amara","orcid":"https://orcid.org/0000-0002-4521-0867","observed_orcids":["https://orcid.org/0000-0002-4521-0867"]},"institutions":[{"id":"https://openalex.org/I118590987","display_name":"Northern Border University","ror":"https://ror.org/03j9tzj20","country_code":"SA","type":"education","lineage":["https://openalex.org/I118590987"]}],"countries":["SA"],"is_corresponding":true,"raw_author_name":"Marwa Amara","raw_affiliation_strings":["Department of Computer Science, College of Sciences, Northern Border University, 73213, Arar, Kingdom of Saudi Arabia"],"raw_orcid":"https://orcid.org/0000-0002-4521-0867","affiliations":[{"raw_affiliation_string":"Department of Computer Science, College of Sciences, Northern Border University, 73213, Arar, Kingdom of Saudi Arabia","institution_ids":["https://openalex.org/I118590987"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020905060","display_name":"Nadia Smairi","orcid":"https://orcid.org/0000-0001-5568-8832","observed_orcids":["https://orcid.org/0000-0001-5568-8832"]},"institutions":[{"id":"https://openalex.org/I4405260920","display_name":"National School of Computer Science","ror":"https://ror.org/04g1met76","country_code":"TN","type":"education","lineage":["https://openalex.org/I4405260920"]},{"id":"https://openalex.org/I83259278","display_name":"Manouba University","ror":"https://ror.org/0503ejf32","country_code":"TN","type":"education","lineage":["https://openalex.org/I83259278"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Nadia Smairi","raw_affiliation_strings":["LARIA UR22ES01, ENSI, Manouba University, Manouba, Tunisia"],"raw_orcid":"https://orcid.org/0000-0001-5568-8832","affiliations":[{"raw_affiliation_string":"LARIA UR22ES01, ENSI, Manouba University, Manouba, Tunisia","institution_ids":["https://openalex.org/I4405260920","https://openalex.org/I83259278"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5017101202"],"corresponding_institution_ids":["https://openalex.org/I118590987"],"apc_list":{"value":3730,"currency":"USD","value_usd":3730},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"203","issue":null,"first_page":"116272","last_page":"116272"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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/T12535","display_name":"Machine Learning and Data Classification","score":9.999999747378752e-05,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.0,"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/synthetic-oversampling","display_name":"synthetic oversampling","score":0.7820000052452087},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.7319999933242798},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.8669999837875366},{"id":"https://openalex.org/keywords/smote","display_name":"SMOTE","score":0.9490000009536743},{"id":"https://openalex.org/keywords/adasyn","display_name":"ADASYN","score":0.7860000133514404},{"id":"https://openalex.org/keywords/spam-text-message","display_name":"spam SMS","score":0.7360000014305115},{"id":"https://openalex.org/keywords/hate-speech","display_name":"hate speech","score":0.9010000228881836},{"id":"https://openalex.org/keywords/emotion-classification","display_name":"emotion classification","score":0.7990000247955322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6089000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5964000225067139},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.5960000157356262},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5756000280380249},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5450000166893005},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.36640000343322754},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3528999984264374},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.34950000047683716},{"id":"https://openalex.org/C161677786","wikidata":"https://www.wikidata.org/wiki/Q2478475","display_name":"Neighbourhood (mathematics)","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.31049999594688416},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C58471807","wikidata":"https://www.wikidata.org/wiki/Q327120","display_name":"Receiver operating characteristic","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.266400009393692},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.25769999623298645},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2531000077724457},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.asoc.2026.116272","doi":"https://doi.org/10.1016/j.asoc.2026.116272","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.asoc.2026.116272","pdf_url":null,"source":{"id":"https://openalex.org/S140556538","display_name":"Applied Soft Computing","issn_l":"1568-4946","issn":["1568-4946","1872-9681"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","dongbi-c","jufo-1","ki-jl-1","norway-2","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Applied Soft Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1509551116","display_name":null,"funder_award_id":"NBU-FFR-2026-2729-02","funder_id":"https://openalex.org/F4320328654","funder_display_name":"Northern Border University"}],"funders":[{"id":"https://openalex.org/F4320328654","display_name":"Northern Border University","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W28412257","https://openalex.org/W1591261915","https://openalex.org/W1987971958","https://openalex.org/W1993220166","https://openalex.org/W1996523702","https://openalex.org/W2051224630","https://openalex.org/W2059507684","https://openalex.org/W2099454382","https://openalex.org/W2104167780","https://openalex.org/W2107138773","https://openalex.org/W2107686700","https://openalex.org/W2115629999","https://openalex.org/W2118978333","https://openalex.org/W2148143831","https://openalex.org/W2338318698","https://openalex.org/W2562319768","https://openalex.org/W2766296277","https://openalex.org/W2767106145","https://openalex.org/W2769317996","https://openalex.org/W2884561390","https://openalex.org/W2890269216","https://openalex.org/W2917085252","https://openalex.org/W2936503027","https://openalex.org/W2944780533","https://openalex.org/W3095369918","https://openalex.org/W4390781715","https://openalex.org/W4392751407","https://openalex.org/W4409885027","https://openalex.org/W4415974447","https://openalex.org/W7117674035","https://openalex.org/W7131867684","https://openalex.org/W7163326295"],"related_works":["https://openalex.org/W4416620062","https://openalex.org/W4405027859","https://openalex.org/W2969674096","https://openalex.org/W2417855979","https://openalex.org/W144784517","https://openalex.org/W2046989940","https://openalex.org/W4292387278","https://openalex.org/W4205481247","https://openalex.org/W2321113898","https://openalex.org/W7165798645"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2026-08-23T00:00:00"}