{"id":"W2177825695","doi":"","title":"Feature Selection for Sentiment Analysis Based on Content and Syntax Models","year":2011,"lang":"en","type":"article","venue":"The Atrium (University of Guelph)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Sentiment analysis; Feature selection; Lexicon; Artificial intelligence; Salient; Entropy (arrow of time); Natural language processing; Classifier (UML); Feature (linguistics); Syntax; Principle of maximum entropy; Set (abstract data type); Selection (genetic algorithm); Machine learning","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":[0.0002656662,0.00007701977,0.0001651046,0.0002176294,0.0002172223,0.00002082162,0.0003423155,0.00003684197,0.00002632665],"category_scores_gemma":[0.000003487292,0.00006570706,0.0002067712,0.0005364145,0.00003830064,0.0001887606,0.00008111,0.00005024758,0.000002517005],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002294277,"about_ca_system_score_gemma":0.00001452077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002230048,"about_ca_topic_score_gemma":0.00005385295,"domain_scores_codex":[0.9993969,0.00004814483,0.00005884904,0.0002188848,0.000161631,0.0001156454],"domain_scores_gemma":[0.9994311,0.00006004662,0.000121563,0.0002504605,0.00009485555,0.00004202842],"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":[0.003881807,0.002830407,0.1351734,0.0003613739,0.02216682,0.00004231417,0.06322818,0.161908,0.1310793,0.3778981,0.03691792,0.06451243],"study_design_scores_gemma":[0.0003982351,0.0001153174,0.03365333,0.000007111371,0.0005094854,4.474266e-7,0.000642227,0.9633775,0.0007092839,0.0002858569,0.0002142431,0.00008690503],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1056923,0.00005177501,0.89145,0.002100395,0.00004956295,0.0001565781,0.000004516909,0.00003125306,0.0004636537],"genre_scores_gemma":[0.9776847,0.000009572844,0.02147291,0.0000798741,0.00001001537,2.745555e-7,0.00000447132,0.00000236527,0.0007358118],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8719924,"threshold_uncertainty_score":0.2679456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05167030843805941,"score_gpt":0.220040339556439,"score_spread":0.1683700311183796,"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."}}