{"id":"W2251031731","doi":"","title":"A System for Multilingual Sentiment Learning On Large Data Sets","year":2012,"lang":"en","type":"article","venue":"International Conference on Computational Linguistics","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Sentiment analysis; Artificial intelligence; Generalization; Natural language processing; Set (abstract data type); Empirical research; Machine learning; Mathematics","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":[0.0007093772,0.0001889648,0.0001845957,0.0002062242,0.0002406137,0.0002825494,0.001112157,0.00005584858,0.00004771337],"category_scores_gemma":[0.0009112898,0.0001865298,0.00008254754,0.0001165585,0.00001946949,0.0001358329,0.0003532126,0.0001803074,0.0001723096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000113658,"about_ca_system_score_gemma":0.0001004391,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004136902,"about_ca_topic_score_gemma":9.078386e-7,"domain_scores_codex":[0.9979743,0.00006883447,0.0004003835,0.0004720027,0.0007608116,0.0003236182],"domain_scores_gemma":[0.9978701,0.0005516747,0.0002546123,0.0003630813,0.0008352007,0.0001253305],"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":[0.00002961045,0.0002585658,0.001189919,0.00001397146,0.0001309475,0.000004056611,0.0003153318,0.01970075,0.00001040562,0.9735488,0.001223216,0.003574486],"study_design_scores_gemma":[0.0006025393,0.00007591533,0.0005171645,0.0000966155,0.00001690498,0.000003305246,0.0001584414,0.9659294,0.0001069096,0.001187012,0.0311075,0.0001982393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004318497,0.00003856183,0.9670452,0.0005473822,0.006859912,0.000282611,0.0002675401,0.0002317496,0.02040853],"genre_scores_gemma":[0.9288105,0.000002613125,0.06829973,0.0002587317,0.001151152,0.00001343936,0.001166332,0.00001327738,0.0002842578],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9723617,"threshold_uncertainty_score":0.7606466,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1209313347697141,"score_gpt":0.3898499392076454,"score_spread":0.2689186044379313,"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."}}