{"id":"W4206897013","doi":"10.1109/dasa53625.2021.9682402","title":"A Moroccan News Articles Dataset (MNAD) For Arabic Text Categorization","year":2021,"lang":"en","type":"article","venue":"2021 International Conference on Decision Aid Sciences and Application (DASA)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Support vector machine; Naive Bayes classifier; Confusion matrix; Categorization; Context (archaeology); Arabic; Random forest; Gradient boosting; Confusion; Machine learning; Linguistics; Geography","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0007786501,0.001841126,0.000824433,0.007481261,0.00160183,0.0010749,0.0009804047,0.001382263,0.009086772],"category_scores_gemma":[0.002652671,0.0001981634,0.0007716789,0.004594681,0.0003648844,0.0009087261,0.001050453,0.0009571635,0.01183517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001203839,"about_ca_system_score_gemma":0.001147884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02141751,"about_ca_topic_score_gemma":0.03662929,"domain_scores_codex":[0.9992436,0.0001448355,0.0001221043,0.0001765882,0.0002177926,0.00009510789],"domain_scores_gemma":[0.9986441,0.0002767959,0.0001155271,0.0002191777,0.0005789778,0.0001655201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001786927,0.001762608,0.01972253,0.005028627,0.0003307363,0.003161571,0.001225174,0.003286125,0.02735242,0.001523601,0.6737229,0.2610967],"study_design_scores_gemma":[0.0004107969,0.0006379879,0.1019175,0.0005571384,0.0002187486,0.002379723,0.002705705,0.02406427,0.02302228,0.001174533,0.8427247,0.0001866589],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1743364,0.004950559,0.005024823,0.001067004,0.0008977282,0.001513298,0.7842442,0.009101617,0.01886439],"genre_scores_gemma":[0.05236769,0.0007162977,0.01635966,0.0001707877,0.000149799,0.0009089875,0.9225315,0.0001509143,0.006644269],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02141751,"threshold_uncertainty_score":0.04258567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06935459005021938,"score_gpt":0.3509310044313946,"score_spread":0.2815764143811752,"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."}}