{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006598743,0.002005021,0.001918282,0.003760203,0.001829499,0.006629543,0.003143874,0.002982395,0.019336],"category_scores_gemma":[0.02801484,0.001125534,0.001355685,0.003966614,0.001280925,0.008928945,0.00568815,0.00426898,0.01871702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001335003,"about_ca_system_score_gemma":0.00340205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004493057,"about_ca_topic_score_gemma":0.006955382,"domain_scores_codex":[0.9940446,0.00155366,0.0003764081,0.001553654,0.001997588,0.0004742366],"domain_scores_gemma":[0.9750414,0.01242738,0.001206228,0.003298637,0.007499687,0.0005266413],"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":[0.0007104881,0.0005044303,0.006682115,0.0004902417,0.0001244029,0.0002752134,0.001221434,0.004218165,0.04466652,0.01091051,0.01477796,0.9154185],"study_design_scores_gemma":[0.0001387892,0.0009315854,0.01741103,0.0002453374,0.0004783485,0.0009394418,0.002370573,0.652074,0.1486974,0.1040663,0.0724175,0.0002297376],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02908536,0.0004880759,0.9400401,0.001498777,0.0003200926,0.000683373,0.002391369,0.0139493,0.01154364],"genre_scores_gemma":[0.1906595,0.0003946333,0.7807875,0.0004900927,0.0003765086,0.000431513,0.00513484,0.001860648,0.01986458],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.019336,"threshold_uncertainty_score":0.06468529,"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."}}