{"id":"W4281740313","doi":"10.1177/23998083221104489","title":"Monitoring the well-being of vulnerable transit riders using machine learning based sentiment analysis and social media: Lessons from COVID-19","year":2022,"lang":"en","type":"article","venue":"Environment and Planning B Urban Analytics and City Science","topic":"Urban Transport and Accessibility","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Social distance; Public transport; Pandemic; Data collection; Population; Transit (satellite); Social media; Public health; Business; Mass gathering; Ethnic group; Psychology; Coronavirus disease 2019 (COVID-19); Advertising; Geography; Applied psychology; Public relations; Political science; Environmental health; Transport engineering; Medicine; Sociology; Engineering","routes":{"ca_aff":true,"ca_fund":false,"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":["sts"],"consensus_categories":[],"category_scores_codex":[0.002170198,0.0001149551,0.0002199662,0.0001522121,0.004778148,0.00014075,0.000204517,0.00003311938,0.0001719625],"category_scores_gemma":[0.00005209747,0.0001015274,0.00006150082,0.0004412929,0.001136851,0.0001579393,0.00008527272,0.0002931381,8.318583e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001079511,"about_ca_system_score_gemma":0.00009042387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004674196,"about_ca_topic_score_gemma":0.0002447843,"domain_scores_codex":[0.9983096,0.0001892631,0.0002046099,0.000383242,0.0006486696,0.0002646334],"domain_scores_gemma":[0.9992273,0.0003621195,0.0001442513,0.0000995692,0.000009438077,0.0001572813],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001264544,0.00002192277,0.951189,0.000006182747,0.00004990837,0.000004103502,0.02922481,0.01888451,0.0004158352,0.00006979868,0.000002782885,0.0001185438],"study_design_scores_gemma":[0.0005463443,0.00003346252,0.7551491,0.00001398218,0.0009589962,3.368375e-7,0.03436542,0.2054698,0.0006287327,0.0005993868,0.001884671,0.0003497241],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9948796,0.000582083,0.003333316,0.0009394922,0.0000561905,0.00007872005,0.00002288346,0.00001159716,0.00009610964],"genre_scores_gemma":[0.9995217,0.00005599973,0.0002178965,0.00007400154,0.00005537973,0.000002128781,0.00001016528,0.000003925495,0.00005876724],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1960398,"threshold_uncertainty_score":0.9965175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04343184087099614,"score_gpt":0.2973776065069751,"score_spread":0.2539457656359789,"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."}}