{"id":"W6966757674","doi":"10.4224/8914027","title":"Unsupervised learning of semantic orientation from a hundred-billion-word corpus","year":2002,"lang":"en","type":"report","venue":"NPARC","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pointwise mutual information; Pointwise; Orientation (vector space); Word (group theory); Unsupervised learning; Simple (philosophy); Character (mathematics); Semantics (computer science)","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":[0.001236773,0.0009453947,0.0006312738,0.001844218,0.0006060592,0.0009103167,0.0006374901,0.0007898818,0.0009490122],"category_scores_gemma":[0.007961667,0.000332185,0.0006498605,0.001484002,0.0007256306,0.001754262,0.0008834805,0.001027569,0.00100438],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006016226,"about_ca_system_score_gemma":0.0009311793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003103185,"about_ca_topic_score_gemma":0.00667156,"domain_scores_codex":[0.9990221,0.0003548508,0.00009213099,0.0002550994,0.000216223,0.00005949989],"domain_scores_gemma":[0.996253,0.002617339,0.0002009843,0.0003437874,0.000517614,0.00006734353],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009615656,0.0008479691,0.03391619,0.0008834635,0.0004006732,0.0007487085,0.001191772,0.04608645,0.04580687,0.005542479,0.02619364,0.8374203],"study_design_scores_gemma":[0.0002116581,0.0003288577,0.04779113,0.000112778,0.0002380692,0.0008123425,0.001186464,0.8702776,0.04055297,0.01697819,0.02140494,0.0001049798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7495988,0.001203841,0.2246858,0.0006672924,0.0001987043,0.0005677843,0.007133493,0.005388874,0.01055543],"genre_scores_gemma":[0.7773297,0.0004876846,0.1895242,0.0001591855,0.0001057552,0.0006333114,0.02729792,0.0003113903,0.004150826],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003103185,"threshold_uncertainty_score":0.006540716,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04315790005823389,"score_gpt":0.2862517840292877,"score_spread":0.2430938839710539,"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."}}