{"id":"W2467186984","doi":"10.18653/v1/s15-2078","title":"SemEval-2015 Task 10: Sentiment Analysis in Twitter","year":2015,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":367,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"SemEval; Sentiment analysis; Computer science; Task (project management); Context (archaeology); Phrase; Polarity (international relations); Natural language processing; Set (abstract data type); Artificial intelligence; History","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000719636,0.0001267644,0.0002589976,0.0006170032,0.00002927085,0.0001944897,0.0005227386,0.00003938757,0.00071049],"category_scores_gemma":[0.00001468912,0.0001034552,0.0001703586,0.002175398,0.00001442056,0.0003360118,0.0002620313,0.00006015093,0.0007224132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006741666,"about_ca_system_score_gemma":0.00004121067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001191822,"about_ca_topic_score_gemma":0.00005781369,"domain_scores_codex":[0.9984243,0.00008409412,0.0003242063,0.0004180089,0.0004819314,0.0002674958],"domain_scores_gemma":[0.9990816,0.0000282657,0.00007911665,0.0005603993,0.0000926031,0.0001580336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002828995,0.0007902035,0.5436429,0.00001013533,0.002534614,0.0001213231,0.008994191,0.01782308,0.0009271685,0.01156453,0.4018403,0.01172323],"study_design_scores_gemma":[0.00118276,0.00007391698,0.01940571,0.000009806876,0.0002348031,0.000002347676,0.0006251551,0.9408771,0.001853959,0.0007685985,0.03446763,0.0004982579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2125897,0.0003983101,0.721103,0.007002571,0.000550626,0.0002311716,0.00000110452,0.0002653401,0.05785811],"genre_scores_gemma":[0.960225,0.000003461765,0.01976221,0.0007561491,0.00005913628,0.000007830093,0.00001160362,0.000005800785,0.01916874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.923054,"threshold_uncertainty_score":0.9285401,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04611232732077405,"score_gpt":0.3102190803927146,"score_spread":0.2641067530719405,"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."}}