{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004855364,0.003532412,0.001639313,0.002494552,0.002303916,0.002836821,0.002344392,0.002974262,0.01449596],"category_scores_gemma":[0.01365052,0.0005314706,0.002125517,0.00190292,0.0006620192,0.003809893,0.004560092,0.002852555,0.01751044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001530096,"about_ca_system_score_gemma":0.002145712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005648279,"about_ca_topic_score_gemma":0.01693293,"domain_scores_codex":[0.9953349,0.002069933,0.0003231544,0.000924163,0.000839491,0.0005082981],"domain_scores_gemma":[0.994823,0.002254331,0.0002880958,0.0009388553,0.001218903,0.0004768396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001292428,0.0008549349,0.00780597,0.001283749,0.0003428504,0.0004614247,0.0006483246,0.004326859,0.01392888,0.002734084,0.7834954,0.1828252],"study_design_scores_gemma":[0.001196566,0.001366013,0.03585536,0.0003805334,0.0003310865,0.00128986,0.002504771,0.2165587,0.0498554,0.0232915,0.6670153,0.0003548748],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2626034,0.005967896,0.2050616,0.008493613,0.009348478,0.004886213,0.3509048,0.08817875,0.06455527],"genre_scores_gemma":[0.2221258,0.0008096695,0.2182395,0.002088982,0.001533025,0.004490847,0.5070592,0.005309952,0.03834299],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01449596,"threshold_uncertainty_score":0.04849386,"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."}}