{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001224838,0.001494647,0.0008001857,0.001971204,0.0005168444,0.001214538,0.001140534,0.0009399743,0.008893192],"category_scores_gemma":[0.004861128,0.0003800997,0.0009859467,0.0007211967,0.0005169038,0.003998726,0.001865845,0.001604777,0.009897321],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006101176,"about_ca_system_score_gemma":0.001143294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004564383,"about_ca_topic_score_gemma":0.004790068,"domain_scores_codex":[0.9991121,0.0002042438,0.00008143291,0.000333466,0.0002006197,0.00006811714],"domain_scores_gemma":[0.9983558,0.0008096971,0.0001271419,0.0001977108,0.0004176945,0.00009188998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001158094,0.0003396937,0.003223405,0.0006805105,0.0001426081,0.000760622,0.0005835752,0.01901552,0.08061684,0.004638625,0.02627708,0.8625634],"study_design_scores_gemma":[0.00009861721,0.0004278788,0.002260808,0.0000558562,0.00009755523,0.001001591,0.0003815865,0.9014112,0.06106307,0.005616029,0.02744272,0.0001430588],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08470656,0.001253613,0.8213934,0.0007993333,0.0005612773,0.0007622121,0.005769128,0.07556108,0.009193315],"genre_scores_gemma":[0.440721,0.000698214,0.5242538,0.0007271655,0.0002147934,0.0005904002,0.0168965,0.002116248,0.01378182],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008893192,"threshold_uncertainty_score":0.0297507,"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."}}