{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002185048,0.0008142735,0.0008364612,0.002684454,0.0004208437,0.000990056,0.0005525142,0.0005748536,0.001975749],"category_scores_gemma":[0.005933347,0.0001901232,0.001100516,0.001571892,0.0003129242,0.00134815,0.0005176865,0.0008088574,0.001141531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000548284,"about_ca_system_score_gemma":0.0005441067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008990485,"about_ca_topic_score_gemma":0.0009567728,"domain_scores_codex":[0.9990472,0.0003562146,0.0001008892,0.0001451051,0.0002780872,0.0000725128],"domain_scores_gemma":[0.9977624,0.00131161,0.000182497,0.0001312522,0.000568694,0.00004359399],"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":[0.0006110461,0.0003094697,0.009795151,0.0002721456,0.0002107854,0.0002568769,0.0002188381,0.02572737,0.05099406,0.005886761,0.01347166,0.8922458],"study_design_scores_gemma":[0.000103639,0.0002374027,0.008956366,0.00004191953,0.0001334593,0.000214493,0.0001214109,0.948917,0.02172787,0.01434847,0.00514777,0.00005011851],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08140466,0.0005011192,0.9116648,0.0004320437,0.00009323429,0.0003833009,0.0008370154,0.002579989,0.002103825],"genre_scores_gemma":[0.6695674,0.0003642449,0.3236267,0.0001488618,0.0001947912,0.0006946806,0.003263508,0.0001917756,0.001948162],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002684454,"threshold_uncertainty_score":0.01155579,"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."}}