{"id":"W4385078339","doi":"10.18280/isi.280302","title":"Advancements in Semantic Expansion Techniques for Short Text Classification and Hate Speech Detection","year":2023,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Voice activity detection; Artificial intelligence; Speech recognition; Speech processing","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001272698,0.001192447,0.0008259494,0.005047674,0.0006790439,0.001036028,0.0008228954,0.0007964468,0.002728981],"category_scores_gemma":[0.00371807,0.0002162645,0.0008782265,0.002588697,0.0007919661,0.003684433,0.001029051,0.001446201,0.002223374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006039439,"about_ca_system_score_gemma":0.0009169849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002814773,"about_ca_topic_score_gemma":0.003854322,"domain_scores_codex":[0.9983962,0.0004509732,0.0001229079,0.0004081215,0.0005265572,0.00009523],"domain_scores_gemma":[0.9970543,0.001170802,0.0003613642,0.0004232199,0.0008863473,0.0001040078],"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":[0.0001897886,0.0002451812,0.00492768,0.0003144045,0.00007007737,0.000140962,0.0005153164,0.006173546,0.03935206,0.007228349,0.00557391,0.9352686],"study_design_scores_gemma":[0.00003803735,0.0005348274,0.03245235,0.0003057111,0.0001988309,0.001126657,0.001426333,0.8168584,0.05344746,0.03455766,0.05885237,0.0002014511],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08224621,0.003992925,0.8954777,0.000881009,0.0003487735,0.0003936897,0.001311049,0.004328209,0.01102035],"genre_scores_gemma":[0.5319041,0.002925229,0.4500592,0.0003759832,0.0007147738,0.0004143628,0.004413518,0.0002912441,0.008901554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005047674,"threshold_uncertainty_score":0.009129286,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02039985758425538,"score_gpt":0.2595487343813367,"score_spread":0.2391488767970814,"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."}}