{"id":"W2950680175","doi":"10.1109/ms.2019.2923408","title":"Can a Machine Learn Through Customer Sentiment?: A Cost-Aware Approach to Predict Support Ticket Escalations","year":2019,"lang":"en","type":"article","venue":"IEEE Software","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Ticket; Computer science; Happiness; Sentiment analysis; Mechanism (biology); Customer retention; Artificial intelligence; Machine learning; Knowledge management; Marketing; Business; Computer security; Psychology; Service (business)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002351541,0.0002497513,0.0003231772,0.000194654,0.0002774466,0.000175964,0.0007817413,0.00009079371,0.0003732793],"category_scores_gemma":[0.00002322427,0.0002307515,0.0001879902,0.0008656092,0.00002867689,0.0004316209,0.0003276413,0.0002024704,0.001325968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000810488,"about_ca_system_score_gemma":0.0001018635,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009787321,"about_ca_topic_score_gemma":0.00001428758,"domain_scores_codex":[0.9977889,0.00007186086,0.0003546805,0.0007149194,0.0005904732,0.0004791799],"domain_scores_gemma":[0.9986359,0.00006594975,0.0001240496,0.0008504781,0.000121523,0.0002020633],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005295574,0.001550332,0.6669636,0.0002241108,0.001279691,0.00004413726,0.03258937,0.0437044,0.0005624349,0.006627101,0.204938,0.04146378],"study_design_scores_gemma":[0.006223643,0.0007213514,0.04249526,0.000269139,0.0004281492,0.0001269223,0.001287083,0.5584804,0.003557673,0.0009386799,0.3820947,0.003377003],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04014233,0.00005548157,0.9488209,0.00123054,0.001256251,0.001107189,0.00008784431,0.0006292182,0.00667024],"genre_scores_gemma":[0.9295119,0.000008159252,0.05531445,0.001511776,0.000152311,0.00009465722,0.0002210566,0.00003960176,0.01314605],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8935065,"threshold_uncertainty_score":0.9994516,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02302491816982375,"score_gpt":0.2671272912724126,"score_spread":0.2441023731025888,"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."}}