{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000430915,0.000187859,0.0001977679,0.0001661729,0.00009840248,0.0004549865,0.00005408322,0.00004543247,0.00003321348],"category_scores_gemma":[0.00001978657,0.0001613723,0.00003891685,0.0001889962,0.00001591148,0.001227688,0.00005087786,0.0001761916,0.00006274416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003728944,"about_ca_system_score_gemma":0.00000949845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001640283,"about_ca_topic_score_gemma":1.632124e-7,"domain_scores_codex":[0.9990832,0.000003450882,0.0003222418,0.0001940502,0.0001904464,0.0002066328],"domain_scores_gemma":[0.9997214,0.0000244179,0.000074208,0.0001116185,0.00004226593,0.00002606635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004177867,0.0001979985,0.000219736,0.3439059,0.0002741412,0.00002038906,0.001527638,0.3993174,0.01121906,0.05254443,0.002757297,0.1879742],"study_design_scores_gemma":[0.000112268,0.000007532185,0.00001151941,0.002132074,0.00009805315,0.00002302488,0.00001229507,0.9932621,0.000047989,0.0003159956,0.003784828,0.0001923406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0446416,0.005426687,0.9471347,0.0006659967,0.0002455385,0.0007048706,0.000006765331,0.0004116258,0.0007621936],"genre_scores_gemma":[0.987263,0.001630676,0.01021305,0.0002885936,0.0001971639,0.0000529718,0.0001428123,0.00004358897,0.0001681291],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9426214,"threshold_uncertainty_score":0.658057,"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."}}