{"id":"W4385572562","doi":"10.18653/v1/2023.semeval-1.315","title":"SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)","year":2023,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"SemEval; Computer science; Sentiment analysis; Task (project management); Natural language processing; Artificial intelligence; Management","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":[0.007316712,0.003766049,0.00150907,0.003255753,0.002647807,0.003037044,0.002008751,0.003423539,0.01593677],"category_scores_gemma":[0.01062636,0.0005655827,0.001983198,0.002112589,0.0007752709,0.004028799,0.005365881,0.00316591,0.0209585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001318609,"about_ca_system_score_gemma":0.002424496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01052331,"about_ca_topic_score_gemma":0.01646309,"domain_scores_codex":[0.9959285,0.002052367,0.0003396361,0.0005933058,0.0007019374,0.000384242],"domain_scores_gemma":[0.9953468,0.001667468,0.0002502349,0.0007496799,0.001421439,0.0005642939],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0010041,0.0005510144,0.003422199,0.001449853,0.0001937146,0.0005115637,0.0006742554,0.001136485,0.01049023,0.001375959,0.8619169,0.1172737],"study_design_scores_gemma":[0.002204565,0.0008902153,0.03645401,0.001076317,0.0004430213,0.002072947,0.006936674,0.06741361,0.04552711,0.01149698,0.8251168,0.0003678409],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"other","genre_scores_codex":[0.1779561,0.007902987,0.05611734,0.009368567,0.00865341,0.004763664,0.6524248,0.04063739,0.04217577],"genre_scores_gemma":[0.1260488,0.0009981754,0.08673518,0.001347219,0.0006030202,0.00359153,0.756805,0.002567379,0.02130359],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01593677,"threshold_uncertainty_score":0.05331379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03172911908924325,"score_gpt":0.3074321463866484,"score_spread":0.2757030272974051,"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."}}