{"id":"W6920552191","doi":"10.60692/7yqwd-3rk86","title":"SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Task (project management); Sentiment analysis; SemEval; Languages of Africa; Task analysis","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":[0.009221613,0.003982404,0.002294022,0.00331562,0.003708539,0.003546251,0.002522297,0.003979795,0.01868358],"category_scores_gemma":[0.01466364,0.0006090744,0.002136138,0.002536635,0.0009444175,0.003686546,0.006160532,0.003335179,0.0185841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001996194,"about_ca_system_score_gemma":0.004318801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01024623,"about_ca_topic_score_gemma":0.02287182,"domain_scores_codex":[0.9928196,0.002959127,0.0005396072,0.001290859,0.001496748,0.0008941001],"domain_scores_gemma":[0.9888254,0.003482033,0.0004186368,0.001595183,0.003991561,0.001687253],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001110467,0.001045264,0.003583424,0.001732035,0.0002730647,0.0004953615,0.0008916953,0.001888491,0.01842034,0.00104677,0.8072174,0.1622956],"study_design_scores_gemma":[0.001537746,0.001643419,0.02940105,0.0005641513,0.0003481639,0.00166217,0.003814273,0.06122882,0.04764573,0.00727695,0.8444821,0.0003954619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.3046533,0.01087806,0.1010379,0.01256065,0.01618015,0.009579292,0.3639671,0.07257736,0.1085662],"genre_scores_gemma":[0.2158991,0.001096626,0.1709193,0.003080619,0.001679648,0.005763662,0.5342371,0.00608903,0.06123483],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01868358,"threshold_uncertainty_score":0.0625028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04113118126596096,"score_gpt":0.256651799655822,"score_spread":0.2155206183898611,"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."}}