{"id":"W4313343184","doi":"10.1007/978-3-031-23028-8_8","title":"Sentiment Analysis from User Reviews Using a Hybrid Generative-Discriminative HMM-SVM Approach","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"","keywords":"Discriminative model; Hidden Markov model; Computer science; Generative grammar; Latent Dirichlet allocation; Artificial intelligence; Support vector machine; Sentiment analysis; Machine learning; Task (project management); Generative model; Context (archaeology); Process (computing); Natural language processing; Topic model; Engineering","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":[0.0006744218,0.0008683751,0.001143545,0.0009771315,0.0004036753,0.0007706952,0.0005685653,0.000693237,0.002527769],"category_scores_gemma":[0.001261604,0.0003587524,0.001188059,0.0009057123,0.0001673793,0.0007437801,0.000610327,0.0008656989,0.004021122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002674841,"about_ca_system_score_gemma":0.0004698882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002712741,"about_ca_topic_score_gemma":0.004787795,"domain_scores_codex":[0.9994992,0.0001117624,0.00003668181,0.0001292631,0.0001395118,0.00008358282],"domain_scores_gemma":[0.9993004,0.0002441795,0.00004956967,0.00006635408,0.0002962467,0.00004332199],"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":[0.0006746767,0.0004043463,0.008328734,0.0002771642,0.0003047405,0.0002385309,0.0001662038,0.03264901,0.09736381,0.001378436,0.01047558,0.8477387],"study_design_scores_gemma":[0.00001868533,0.0001418484,0.006415207,0.00001740155,0.0001129717,0.000162905,0.00005950323,0.9762305,0.01301306,0.001390572,0.002408625,0.00002864413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07859092,0.001002421,0.911391,0.0002873805,0.0003001531,0.0001363298,0.0009339346,0.00417511,0.003182702],"genre_scores_gemma":[0.7609761,0.0008418919,0.2173529,0.0002202432,0.0004720794,0.0002079263,0.00428571,0.0004317343,0.01521143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002712741,"threshold_uncertainty_score":0.00845623,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05459002356564102,"score_gpt":0.2907508150165164,"score_spread":0.2361607914508754,"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."}}