{"id":"W4286517983","doi":"10.18280/ria.360315","title":"Arabic Language Modeling Based on Supervised Machine Learning","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Misinformation; Arabic; Natural language processing; Machine translation; Python (programming language); Sentiment analysis; Supervised learning; Support vector machine; Machine learning; Artificial neural network; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001237993,0.000100453,0.0001189877,0.000158863,0.001370613,0.00008817929,0.0003081016,0.00003548151,0.007983614],"category_scores_gemma":[0.0004472001,0.0001065458,0.00008272412,0.0005291923,0.00004748306,0.0001590975,0.00005101005,0.0003562724,0.0004165637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001411503,"about_ca_system_score_gemma":0.000111676,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000649657,"about_ca_topic_score_gemma":0.00007976333,"domain_scores_codex":[0.9985161,0.0002552117,0.0002692986,0.0001856584,0.0004376261,0.0003360758],"domain_scores_gemma":[0.9993902,0.000139606,0.00007016808,0.0002219035,0.00004733916,0.00013076],"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":[0.00002180938,0.00006110674,0.00005719571,0.00000772478,0.000002153666,0.000004581443,0.04836766,0.9256854,0.000176866,0.004961897,0.000150681,0.02050291],"study_design_scores_gemma":[0.0000406653,0.00008238522,0.000002300127,0.00001302056,0.000003153737,0.000001021774,0.05352617,0.9193426,0.0006374468,0.00008505253,0.0261392,0.000126958],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5482727,0.0004643063,0.1867973,0.006152736,0.0008871204,0.0007812832,0.00003123497,0.0005771915,0.2560361],"genre_scores_gemma":[0.9907432,0.00002787225,0.0001818742,0.0008897386,0.00007255433,0.000009556225,0.00002725282,0.00001290418,0.008035028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4424705,"threshold_uncertainty_score":0.9999295,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05885087019546301,"score_gpt":0.313653414402295,"score_spread":0.254802544206832,"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."}}