{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000851467,0.0002356556,0.0004304369,0.0010327,0.0002586344,0.0003797477,0.0008681414,0.00006565346,0.0004299111],"category_scores_gemma":[0.00004354348,0.0002027061,0.0006858333,0.003997024,0.00002907838,0.0002919912,0.0004022845,0.00007260679,0.0006900702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004773927,"about_ca_system_score_gemma":0.00003472559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001043216,"about_ca_topic_score_gemma":0.0001215864,"domain_scores_codex":[0.9975082,0.00007698147,0.0004555298,0.0007652394,0.000613204,0.000580808],"domain_scores_gemma":[0.9984839,0.0002246327,0.0001709861,0.0008418349,0.0001141702,0.0001644571],"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":[0.00007180497,0.000926805,0.1371543,0.0001999326,0.0217285,0.0001851275,0.01154095,0.02314512,0.02635181,0.07199073,0.638592,0.06811295],"study_design_scores_gemma":[0.000947173,0.0001063176,0.02118638,0.00001791502,0.001084497,0.00000167471,0.002622494,0.9020751,0.006158414,0.0006642565,0.06436291,0.0007728939],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04895758,0.0002987132,0.9248164,0.006219373,0.0008296859,0.0007200191,0.00006314807,0.001414162,0.01668093],"genre_scores_gemma":[0.8908055,0.0000701264,0.02994284,0.0005480896,0.0003190798,0.0001444477,0.0003279542,0.00003540646,0.07780652],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8948736,"threshold_uncertainty_score":0.8869686,"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."}}