{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001048535,0.0009282792,0.000573263,0.003143951,0.0009707142,0.000954659,0.0007408424,0.00112743,0.002253864],"category_scores_gemma":[0.005680041,0.0002176019,0.0008311135,0.001847097,0.0003889993,0.001282093,0.0008031566,0.001147931,0.002216828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005467463,"about_ca_system_score_gemma":0.0008266297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004480028,"about_ca_topic_score_gemma":0.005755702,"domain_scores_codex":[0.9991145,0.0002108939,0.0001627016,0.000237865,0.0001787762,0.00009528015],"domain_scores_gemma":[0.997252,0.001471651,0.0002385294,0.0002188935,0.0007019401,0.0001169133],"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":[0.001073882,0.001858301,0.1140689,0.00152163,0.000205537,0.002186502,0.001954948,0.02862133,0.03931005,0.001995625,0.0249257,0.7822776],"study_design_scores_gemma":[0.00009342703,0.0007287299,0.1120915,0.000411938,0.00023859,0.001625102,0.0061449,0.772522,0.06303252,0.005824615,0.03716366,0.0001230007],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9007644,0.002494057,0.06702629,0.002619,0.0004191578,0.0007531046,0.01621198,0.002297322,0.007414538],"genre_scores_gemma":[0.8844972,0.0008134195,0.0891349,0.0002305181,0.0001203798,0.0006483386,0.02026871,0.00004868537,0.00423795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004480028,"threshold_uncertainty_score":0.008907914,"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."}}