{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006706106,0.0001420151,0.0001426106,0.0006260942,0.0002445354,0.0002742599,0.0001798793,0.0001143017,0.0000011934],"category_scores_gemma":[0.0001268494,0.0001461928,0.00003508048,0.0009239055,0.00003847781,0.003730411,0.00007409361,0.00009200202,0.0000418314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002224655,"about_ca_system_score_gemma":0.00002925637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004873504,"about_ca_topic_score_gemma":0.00004022952,"domain_scores_codex":[0.9987988,0.00003842726,0.0004518414,0.0002107771,0.0002144649,0.0002856784],"domain_scores_gemma":[0.9993773,0.00004743188,0.0001336716,0.0002449544,0.0001455463,0.00005116911],"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":[0.00002145686,0.000009184447,0.0005626458,0.0001542454,0.000004798431,0.000001167833,0.001086167,0.00004614186,0.0162295,0.0007066167,0.00004398751,0.9811341],"study_design_scores_gemma":[0.0008542709,0.0005588314,0.07921242,0.0005118616,0.00001604433,0.00009123923,0.001320064,0.5885223,0.2964303,0.02212509,0.009660076,0.0006975469],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4090931,0.00001761591,0.5888255,0.0000660601,0.0002556474,0.0007067424,0.000002909415,0.0005621976,0.0004703002],"genre_scores_gemma":[0.9869743,0.0001040185,0.01241647,0.00005305567,0.00003301135,0.0003183982,0.00004535789,0.000009283013,0.00004607531],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9804366,"threshold_uncertainty_score":0.596157,"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."}}