{"id":"W4285115467","doi":"10.18653/v1/2022.wassa-1.13","title":"Assessment of Massively Multilingual Sentiment Classifiers","year":2022,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Department of Artificial Intelligence, Korea University; European Regional Development Fund; Politechnika Wrocławska","keywords":"Sentiment analysis; Subjectivity; Computer science; Social media; Artificial intelligence; Data science; Natural language processing; World Wide Web; Epistemology","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":[0.0003848674,0.00007774081,0.0001466182,0.0001509294,0.0001718966,0.00003982834,0.0005447427,0.00001162845,0.0007642272],"category_scores_gemma":[0.000004659193,0.00007240075,0.0001196765,0.0003829859,0.00001831541,0.0001110941,0.0005937952,0.00009632981,0.000007047867],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006594656,"about_ca_system_score_gemma":0.00008516679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001556466,"about_ca_topic_score_gemma":7.83126e-7,"domain_scores_codex":[0.9986797,0.00008446169,0.0002662881,0.0002693044,0.0005412003,0.0001590494],"domain_scores_gemma":[0.9993926,0.00004759202,0.0001499146,0.0003199707,0.00004125558,0.00004867768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001412507,0.001700192,0.1250801,0.00003483336,0.000797444,0.00007977068,0.003680622,0.0359439,0.0461551,0.6906066,0.01813646,0.07777092],"study_design_scores_gemma":[0.000636593,0.0001620248,0.02555543,0.000004103255,0.00001990411,0.000004582623,0.001688645,0.9526228,0.006695932,0.000278539,0.01211545,0.0002159943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2456953,0.00008877121,0.7053586,0.00148963,0.001295913,0.0002661177,0.000006148377,0.0001690504,0.04563038],"genre_scores_gemma":[0.9278002,0.000002366981,0.06983779,0.000178049,0.00001484192,0.00001326042,0.00000708595,0.000003680678,0.002142724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9166789,"threshold_uncertainty_score":0.8367751,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02674224008336883,"score_gpt":0.3108617894804158,"score_spread":0.284119549397047,"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."}}