{"id":"W4416504162","doi":"10.1038/s41598-025-25879-4","title":"Tackling toxicity in Arabic social media through advanced detection techniques","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Minia University","keywords":"Arabic; Social media; Embedding; Interpersonal communication; Encoder; Transformer","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":[0.0008047796,0.001661903,0.0006375794,0.003900923,0.0007832305,0.001144767,0.0008352638,0.000952194,0.001261755],"category_scores_gemma":[0.003817274,0.0001939518,0.0007037903,0.001422666,0.000462388,0.002017222,0.001433097,0.0009847784,0.001500518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005848461,"about_ca_system_score_gemma":0.0005406502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004244744,"about_ca_topic_score_gemma":0.006780138,"domain_scores_codex":[0.9989441,0.0002921909,0.0001105785,0.0002227295,0.0003363593,0.00009396433],"domain_scores_gemma":[0.9980102,0.0006322734,0.0003817388,0.0002543351,0.0006439573,0.0000774748],"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":[0.0003922942,0.0005542429,0.05139868,0.0008419732,0.0001710321,0.001667988,0.001047738,0.01973682,0.03518033,0.002439034,0.02095929,0.8656105],"study_design_scores_gemma":[0.00004327525,0.0005757023,0.05862515,0.0003008388,0.0002141085,0.002973133,0.003373615,0.7930874,0.07283101,0.01066313,0.05715061,0.0001620803],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7224727,0.007590564,0.231267,0.002435159,0.0008760275,0.000858043,0.009547527,0.007429189,0.01752369],"genre_scores_gemma":[0.8526012,0.002598254,0.1212489,0.0004522127,0.0003503662,0.0004215365,0.01186823,0.0001569609,0.0103023],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004244744,"threshold_uncertainty_score":0.008440077,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00994106582999158,"score_gpt":0.2583990237387625,"score_spread":0.2484579579087709,"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."}}