{"id":"W2747541555","doi":"10.18653/v1/w17-5205","title":"WASSA-2017 Shared Task on Emotion Intensity","year":2017,"lang":"en","type":"preprint","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Sadness; Task (project management); Computer science; Anger; Emotion classification; Artificial intelligence; Natural language processing; 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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004482169,0.0002585372,0.0004030836,0.0002096976,0.0002954491,0.00124657,0.002160021,0.0002156224,0.0001265315],"category_scores_gemma":[0.00008667117,0.0002189946,0.0003061622,0.0000572949,0.00003250805,0.0002758384,0.002530752,0.0004249055,0.0005686776],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006759568,"about_ca_system_score_gemma":0.00006532368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009091091,"about_ca_topic_score_gemma":0.00001017361,"domain_scores_codex":[0.9980981,0.00005038797,0.0002840455,0.0008838548,0.000439537,0.0002440455],"domain_scores_gemma":[0.996932,0.00003409088,0.0004221156,0.002317581,0.0001943193,0.00009983456],"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":[0.00005165292,0.0005714535,0.01076921,0.0001645155,0.001008734,0.0001685003,0.003226278,0.003484316,0.0005506414,0.06202325,0.8047142,0.1132673],"study_design_scores_gemma":[0.0004922387,0.0001071013,0.05376296,0.0005926399,0.00007466927,0.000008471649,0.00005920543,0.9160352,0.001684483,0.01123387,0.01488878,0.00106042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03859374,0.000158361,0.8010096,0.009808097,0.01013785,0.0005383811,0.00001862044,0.0007536781,0.1389817],"genre_scores_gemma":[0.9697042,0.00006872004,0.01974708,0.0006300177,0.0004724982,0.00001138014,0.0001314403,0.00001412539,0.009220599],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9311104,"threshold_uncertainty_score":0.9997903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07464270248836234,"score_gpt":0.3119290040892959,"score_spread":0.2372863016009335,"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."}}