{"id":"W4392191348","doi":"10.18280/mmep.110209","title":"Improving Performance Sentiment Movie Review Classification Using Hybrid Feature TFIDF, N-Gram, Information Gain and Support Vector Machine","year":2024,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"tf–idf; Support vector machine; n-gram; Computer science; Feature (linguistics); Sentiment analysis; Information gain; Information retrieval; Artificial intelligence; Pattern recognition (psychology); Term (time); Physics","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":[0.001361132,0.0009669211,0.0009704502,0.001548554,0.0003158393,0.0006937489,0.0004501932,0.0005494339,0.000575209],"category_scores_gemma":[0.003340801,0.0001640379,0.0005751158,0.0008635367,0.0001215867,0.0009067022,0.0003244953,0.0005156479,0.0006439142],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004440848,"about_ca_system_score_gemma":0.0005427677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00689744,"about_ca_topic_score_gemma":0.006120475,"domain_scores_codex":[0.9992687,0.0001920247,0.00006605492,0.0001255299,0.00025572,0.00009189754],"domain_scores_gemma":[0.998683,0.000448205,0.0001153912,0.00006985907,0.0006273474,0.00005616428],"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":[0.0008943505,0.0003585738,0.01938647,0.0001925627,0.0001854965,0.000185334,0.0001356508,0.02271949,0.04455791,0.0004973934,0.00604163,0.9048451],"study_design_scores_gemma":[0.00001589638,0.0002571271,0.00839234,0.0000102706,0.00004896095,0.0001000766,0.00005436649,0.9726052,0.01720083,0.0002732409,0.001020151,0.00002150896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6503061,0.002821541,0.3375199,0.0005976995,0.000298663,0.000187335,0.000529393,0.003819978,0.003919327],"genre_scores_gemma":[0.9131081,0.0003266728,0.08377936,0.00008130478,0.0001163224,0.0000487186,0.0006508302,0.00004305892,0.001845694],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00689744,"threshold_uncertainty_score":0.01371461,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0229709270418278,"score_gpt":0.2163882120738583,"score_spread":0.1934172850320305,"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."}}