{"id":"W4391554431","doi":"10.1016/j.engappai.2024.107987","title":"AraCovTexFinder: Leveraging the transformer-based language model for Arabic COVID-19 text identification","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Athabasca University","funders":"Athabasca University","keywords":"Computer science; Arabic; Transformer; Coronavirus disease 2019 (COVID-19); Natural language processing; Language model; Artificial intelligence; Identification (biology); Linguistics; Electrical engineering; Infectious disease (medical specialty); Voltage","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00103714,0.00009551569,0.00009071351,0.0001782625,0.0003689948,0.0001740268,0.0003280784,0.0000620219,0.00005734216],"category_scores_gemma":[0.0004044404,0.00008457294,0.0000934529,0.0006151279,0.0001172684,0.0002363448,0.000005360729,0.0001133396,0.00005004423],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001179941,"about_ca_system_score_gemma":0.0004052888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001500976,"about_ca_topic_score_gemma":0.00008266282,"domain_scores_codex":[0.9989648,0.00001768684,0.0003940536,0.0001665414,0.0002475365,0.0002093514],"domain_scores_gemma":[0.9990534,0.0004395858,0.00006337386,0.0002421939,0.00008695719,0.0001145384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005828651,0.00002559237,6.050211e-7,0.0001323876,0.00001081769,8.044718e-8,0.04126477,0.5298521,0.003900266,0.3134958,0.0002491401,0.1110626],"study_design_scores_gemma":[0.00001277912,0.000006326147,0.000004088134,0.00001986003,0.00001652014,3.38525e-7,0.00683477,0.9612812,0.0131058,0.00478505,0.01382749,0.0001057482],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003898867,0.000234468,0.9900904,0.004201954,0.0001082358,0.000802618,0.00004047555,0.000212263,0.0004106936],"genre_scores_gemma":[0.9958148,0.00003631122,0.003321374,0.0001764323,0.0001037213,0.0001892045,0.00002302278,0.0000136304,0.0003215326],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9919159,"threshold_uncertainty_score":0.3448784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06443222881926478,"score_gpt":0.3730806849467553,"score_spread":0.3086484561274906,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}