{"id":"W2471707884","doi":"10.1016/j.dss.2016.06.010","title":"Modeling customer satisfaction from unstructured data using a Bayesian approach","year":2016,"lang":"en","type":"article","venue":"Decision Support Systems","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Customer satisfaction; Computer science; Bayesian probability; Set (abstract data type); Sentiment analysis; Probabilistic logic; Unstructured data; The Internet; Customer intelligence; Data mining; Service (business); Product (mathematics); Bayesian network; Variety (cybernetics); Data set; Data science; Artificial intelligence; Service quality; Customer retention; World Wide Web; Big data; Marketing; Mathematics","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":[0.0007405099,0.0001988351,0.0003633442,0.0002762066,0.0001745497,0.0003947305,0.001223669,0.0001158125,0.0001357647],"category_scores_gemma":[0.00004976338,0.0001292309,0.00008994875,0.0004240757,0.00001705428,0.00134962,0.0005451084,0.0000748226,0.000164027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007451471,"about_ca_system_score_gemma":0.00007890828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005413247,"about_ca_topic_score_gemma":0.00001212812,"domain_scores_codex":[0.9971613,0.0001061395,0.0006902533,0.0009316593,0.0008201189,0.0002904988],"domain_scores_gemma":[0.9974288,0.0001289455,0.0002150364,0.001969991,0.000107647,0.0001495313],"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":[0.00008467906,0.0001267581,0.0673884,0.0000369068,0.0006437503,0.00008316279,0.00159595,0.05180077,0.01923458,0.005645859,0.01877922,0.8345799],"study_design_scores_gemma":[0.0003931202,0.000006923494,0.0003585788,0.00007638326,0.00002370536,0.00002750597,0.0001239732,0.9966027,0.00004283285,0.0002248499,0.00191158,0.0002078161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04412153,0.0001118361,0.9537761,0.00003224852,0.001414404,0.0001410618,0.00003634056,0.00009461653,0.0002718811],"genre_scores_gemma":[0.8677049,0.0000127152,0.1318469,0.00002710317,0.0002376347,0.000003783629,0.00005863854,0.00001562304,0.00009276125],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.944802,"threshold_uncertainty_score":0.5269881,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08640592321187143,"score_gpt":0.3129794778408794,"score_spread":0.226573554629008,"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."}}