{"id":"W3208025439","doi":"10.5815/ijitcs.2021.05.04","title":"Data Mining for Cyberbullying and Harassment Detection in Arabic Texts","year":2021,"lang":"en","type":"article","venue":"International Journal of Information Technology and Computer Science","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Arabic; Computer science; Globe; Scarcity; Harassment; Social media; Artificial intelligence; Natural language processing; World Wide Web; Internet privacy; Data science; Linguistics; Psychology; Social psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008376444,0.00006759393,0.0001006609,0.001035945,0.0001242297,0.0003676816,0.0009667728,0.00005685133,7.559738e-7],"category_scores_gemma":[0.0001834118,0.0000637817,0.00001515678,0.0006343454,0.0001128264,0.003809944,0.000580067,0.0001352217,0.000001009158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005618303,"about_ca_system_score_gemma":0.0001670099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001628722,"about_ca_topic_score_gemma":0.000006676298,"domain_scores_codex":[0.9990203,0.00001286979,0.0003778864,0.0001673375,0.0002868046,0.0001347726],"domain_scores_gemma":[0.9988693,0.0000527101,0.0002605309,0.0002000188,0.0005736959,0.00004374487],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000960683,0.00001505439,0.0006152957,0.000005453768,0.0000112421,0.00001286002,0.0002596181,0.00008333739,0.00133607,0.01035108,0.00002064694,0.9872797],"study_design_scores_gemma":[0.001889514,0.000385601,0.0156986,0.000232727,0.000008549282,0.004556132,0.0003760341,0.8935044,0.05615954,0.01708614,0.009829953,0.0002728073],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2032157,0.00009183505,0.7942085,0.001612016,0.0007651806,0.0000483909,0.000002044911,0.00002185352,0.00003447078],"genre_scores_gemma":[0.7957163,0.00007211482,0.2039134,0.0002449675,0.00004388937,0.000002685194,0.000001652001,0.000001222911,0.000003799582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9870069,"threshold_uncertainty_score":0.3545563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01283397843629926,"score_gpt":0.2658632967070623,"score_spread":0.253029318270763,"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."}}