{"id":"W2949998441","doi":"10.48550/arxiv.cs/0212032","title":"Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews","year":2002,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":1585,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Phrase; Orientation (vector space); Natural language processing; Word (group theory); Computer science; Artificial intelligence; Linguistics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001847947,0.0009526332,0.0009915725,0.003782591,0.000514595,0.001237109,0.0007267687,0.0009406521,0.00124614],"category_scores_gemma":[0.007626206,0.0002559335,0.000724351,0.002289648,0.0005725659,0.001065153,0.0005754678,0.0007130097,0.00105544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006907909,"about_ca_system_score_gemma":0.0008064743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002751257,"about_ca_topic_score_gemma":0.003142884,"domain_scores_codex":[0.9983795,0.0004488662,0.0001829009,0.0004062424,0.0004570645,0.0001254079],"domain_scores_gemma":[0.9969236,0.001592105,0.0004820354,0.0001934373,0.0007345355,0.00007423096],"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":[0.0004887125,0.000248037,0.03791559,0.000293472,0.0003183185,0.0001654629,0.0004898616,0.0165499,0.01434355,0.003833491,0.008973823,0.9163799],"study_design_scores_gemma":[0.00008389108,0.0002250126,0.03847459,0.000105276,0.0001490144,0.0005221175,0.0004053469,0.9183896,0.0132675,0.02132189,0.006966904,0.000088957],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2431534,0.001509253,0.7381621,0.0009997576,0.0003447286,0.0006575873,0.001400648,0.003879878,0.009892613],"genre_scores_gemma":[0.7380538,0.0003737356,0.2568479,0.0002424737,0.0003228698,0.000285121,0.001362897,0.0001097075,0.00240155],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003782591,"threshold_uncertainty_score":0.009773016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1540121900601793,"score_gpt":0.3315217737850789,"score_spread":0.1775095837248996,"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."}}