{"id":"W4381512438","doi":"10.1177/03611981231179167","title":"Using Twitter to Gauge Customer Satisfaction Response to a Major Transit Service Change in Calgary, Canada","year":2023,"lang":"en","type":"article","venue":"Transportation Research Record Journal of the Transportation Research Board","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lexicon; Sentiment analysis; Customer satisfaction; Service quality; Schedule; Computer science; Service (business); Social media; Reliability (semiconductor); Public transport; Loyalty; Marketing; Business; Engineering; Transport engineering; Artificial intelligence; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006139616,0.0002375926,0.0004354842,0.002920867,0.0004566717,0.0002043116,0.001397175,0.0001165977,0.0001448925],"category_scores_gemma":[0.0001139308,0.0001988962,0.0002086951,0.01123561,0.00006068701,0.0008145114,0.00002174962,0.001167453,0.00006503945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006443214,"about_ca_system_score_gemma":0.001244217,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.7315946,"about_ca_topic_score_gemma":0.9458088,"domain_scores_codex":[0.9915608,0.001496399,0.001218867,0.0005508112,0.004114402,0.001058675],"domain_scores_gemma":[0.9958139,0.000771077,0.0002198216,0.0005678631,0.002033038,0.0005943208],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.006067737,0.0002472007,0.8033482,0.0003334194,0.0002960769,0.001259976,0.04623687,0.02130133,0.06794381,0.001105498,0.0272763,0.0245836],"study_design_scores_gemma":[0.001000849,0.0002010846,0.9821561,0.0003382029,0.00001830369,6.147325e-7,0.001716858,0.004839814,0.0009260728,0.0001398099,0.008442525,0.0002197691],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.965916,0.00002928431,0.006731264,0.02568915,0.0005571377,0.00100604,0.00002442366,0.00002858087,0.00001808266],"genre_scores_gemma":[0.9929793,0.0000624445,0.005627323,0.0007867885,0.0001293642,0.000100667,0.000009017939,0.00003837386,0.0002667211],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2142141,"threshold_uncertainty_score":0.8110752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1871371268052244,"score_gpt":0.4163829707673877,"score_spread":0.2292458439621634,"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."}}