{"id":"W2990784666","doi":"10.48550/arxiv.1912.00741","title":"SemEval-2014 Task 9: Sentiment Analysis in Twitter","year":2019,"lang":"en","type":"preprint","venue":"NPARC","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"SemEval; Computer science; Task (project management); Sentiment analysis; Point (geometry); Natural language processing; Artificial intelligence; Scale (ratio); Arabic; Information retrieval; Linguistics; Geography; Mathematics; Cartography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007844055,0.000336047,0.0007604689,0.001205493,0.00004552585,0.0004174148,0.001510804,0.0002143688,0.001032228],"category_scores_gemma":[0.00001103907,0.000316969,0.0006594772,0.001078686,0.00002335812,0.0001520285,0.002118771,0.0004736841,0.0007408757],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001322324,"about_ca_system_score_gemma":0.00009838574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006066157,"about_ca_topic_score_gemma":0.00001953187,"domain_scores_codex":[0.996882,0.0001862003,0.0006212921,0.001170682,0.0007094585,0.0004303355],"domain_scores_gemma":[0.9976062,0.00007379773,0.0003439643,0.001792616,0.00008305115,0.0001003567],"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":[0.0000310938,0.0009485765,0.6299343,0.0003379056,0.01039263,0.0001740828,0.009191144,0.1634776,0.008841859,0.009374479,0.1468346,0.02046173],"study_design_scores_gemma":[0.0004955035,0.00002594336,0.02786542,0.0001129058,0.0006223495,0.000001096211,0.00005804572,0.9576065,0.001200383,0.004995008,0.006233573,0.0007832596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2680288,0.0005088557,0.6843909,0.00530852,0.002859255,0.0008174597,0.00001620491,0.0002602999,0.03780973],"genre_scores_gemma":[0.9704746,0.00006895703,0.02480962,0.0006154359,0.000146272,0.00003508425,0.00008547503,0.00001788836,0.003746649],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.794129,"threshold_uncertainty_score":0.9999282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02221473238461399,"score_gpt":0.281182413725846,"score_spread":0.258967681341232,"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."}}