{"id":"W4384346102","doi":"10.1007/978-3-031-37249-0_8","title":"Addressing Biases in the Texts Using an End-to-End Pipeline Approach","year":2023,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Toronto Metropolitan University; University of Toronto","funders":"","keywords":"Pipeline (software); Popularity; Computer science; Social media; Set (abstract data type); Word (group theory); Natural language processing; Artificial intelligence; Information retrieval; Data science; World Wide Web; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002702379,0.0002064851,0.0002056061,0.001530133,0.0006738205,0.001272992,0.00396772,0.0001089787,0.000002895073],"category_scores_gemma":[0.00009798118,0.000174591,0.00003555144,0.001318956,0.0004312461,0.005712143,0.001592796,0.0005028906,0.00004255989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001216224,"about_ca_system_score_gemma":0.0002750542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007826805,"about_ca_topic_score_gemma":0.00005979525,"domain_scores_codex":[0.9980356,0.00009503841,0.00062127,0.0003347016,0.0005995775,0.000313824],"domain_scores_gemma":[0.9970199,0.0002773993,0.0002250253,0.002159721,0.0002105052,0.0001074013],"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":[0.00000346633,0.00006122182,0.00002943858,0.00003182231,0.000003455782,0.000002229646,0.01081134,0.01578612,0.00002235761,0.1627781,0.0001733438,0.8102971],"study_design_scores_gemma":[0.0001457169,0.00004348563,0.0007337181,0.0002502722,0.000003334017,0.00005358834,0.0001132454,0.9826366,0.00001427644,0.002315675,0.01343605,0.0002540774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001192865,0.0001771532,0.8776134,0.001025029,0.0004889837,0.000916815,0.0000185007,0.0002371291,0.1183301],"genre_scores_gemma":[0.3983003,0.001233376,0.5937615,0.004586582,0.0002345808,0.0001112895,0.000215032,0.00004104748,0.001516238],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9668505,"threshold_uncertainty_score":0.9997638,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2047057078257271,"score_gpt":0.3525948510807206,"score_spread":0.1478891432549936,"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."}}