{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T04:21:15Z","timestamp":1790655675229,"version":"4.1.0"},"reference-count":99,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"vor","delay-in-days":29,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276090"],"award-info":[{"award-number":["62276090"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Risk Analysis"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Urban bus accidents present major safety and operational challenges, particularly in densely populated metropolitan areas. This study develops a machine learning\u2010based analytical framework to identify, quantify, and interpret the factors associated with severe bus accidents. The framework integrates three components: (i) a structural topic model (STM) to extract latent accident scenarios from unstructured narrative data, (ii) an extreme gradient boosting (XGBoost) classifier to predict accident severity, and (iii) SHapley Additive exPlanations (SHAP) for post hoc interpretation of model outputs at both global and local levels. Using over 15,000 bus accident records (2013\u20132018) from a Tier\u20102 city in Jiangsu Province, China, the findings show that incorporating text\u2010derived accident patterns markedly improves both predictive accuracy and interpretability. The analysis highlights elevated risks linked to rear\u2010end collisions involving electric scooters, sudden stops leading to passenger injuries, and left\u2010turn maneuvers in congested areas. SHAP\u2010based explanations yield actionable insights for drivers, transit operators, and policymakers, facilitating targeted safety interventions. Methodologically, this study advances interpretable risk modeling through the integration of structured and unstructured data, and the modular analytical framework provides a transferable foundation for applications across diverse domains of transportation and risk\u00a0analysis.<\/jats:p>","DOI":"10.1111\/risa.70183","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T15:13:07Z","timestamp":1769785987000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["From Prediction to Prevention: Using Text Mining and Explainable Machine Learning for Urban Bus Accident Analytics"],"prefix":"10.1111","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4045-3253","authenticated-orcid":false,"given":"Bowei","family":"Chen","sequence":"first","affiliation":[{"name":"Adam Smith Business School University of Glasgow Glasgow UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1903-0838","authenticated-orcid":false,"given":"Yufei","family":"Huang","sequence":"additional","affiliation":[{"name":"Trinity Business School Trinity College Dublin Dublin Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9046-5511","authenticated-orcid":false,"given":"Yu","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Finance Southwestern University of Finance and Economics Chengdu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1310-6739","authenticated-orcid":false,"given":"Xiaofeng","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence and Automation Hohai University Nanjing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.3141\/2061-07"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.3141\/2136-10"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2015.1051182"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2010.12.024"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2017.04.009"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/atr.104"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwm064"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0386-1112(14)60121-7"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.3.4-5.993"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.3141\/2194-05"},{"key":"e_1_2_9_12_1","first-page":"1877","article-title":"Language Models Are Few\u2010Shot Learners","volume":"33","author":"Brown T. B.","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2009.12.015"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2018.3271"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssci.2012.06.017"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.3141\/1635-13"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2006.04.009"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tourman.2024.105067"},{"key":"e_1_2_9_19_1","first-page":"785","article-title":"XGBoost: A Scalable Tree Boosting System","volume":"8","author":"Chen T.","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2010.06.018"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2012.03.030"},{"issue":"1","key":"e_1_2_9_22_1","first-page":"89","article-title":"Traffic Accident Analysis Using Machine Learning Paradigms","volume":"29","author":"Chong M.","year":"2005","journal-title":"Informatica"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2006.02.013"},{"key":"e_1_2_9_24_1","unstructured":"Department of Transportation Federal Highway Administration.2009. \u201cDedicated Left\u2010and Right\u2010Turn Lanes at Intersections.\u201d Technical Report."},{"key":"e_1_2_9_25_1","first-page":"4171","article-title":"BERT: Pre\u2010Training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin J.","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00325"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0009.12644"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2015.09.025"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1111\/0272-4332.00012"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1111\/0272-4332.00011"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/hsr2.396"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1177\/1748301817729953"},{"key":"e_1_2_9_33_1","doi-asserted-by":"crossref","unstructured":"Gu X. X.Yan L.Ma andX.Liu.2020. \u201cModeling the Service\u2010Route\u2010Based Crash Frequency by a Spatiotemporal\u2010Random\u2010Effect Zero\u2010Inflated Negative Binomial Model: An Empirical Analysis for Bus\u2010Involved Crashes.\u201dAccident Analysis and Prevention144.","DOI":"10.1016\/j.aap.2020.105674"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2939624"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1136\/emj.2003.013128"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tourman.2019.01.002"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0001-4575(01)00086-0"},{"key":"e_1_2_9_38_1","first-page":"17","article-title":"Analysis of Bus Transit Accidents: Empirical, Methodological, and Policy Issues","volume":"1322","author":"Jovanis P. P.","year":"1991","journal-title":"Transportation Research Record"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/risa.14211"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsr.2012.05.003"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.5465\/amj.2019.1340"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103459"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1111\/risa.14215"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tourman.2024.105007"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1111\/risa.70052"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2024.107665"},{"key":"e_1_2_9_47_1","first-page":"141","article-title":"Exploring Injury Severity Patterns in Traffic Crashes Using A Random Forest Approach","volume":"120","author":"Li X.","year":"2018","journal-title":"Accident Analysis & Prevention"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tra.2010.02.001"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1093\/pan\/mpu019"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0138-9"},{"key":"e_1_2_9_51_1","first-page":"4768","article-title":"A Unified Approach to Interpreting Model Predictions","volume":"12","author":"Lundberg S. M.","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"e_1_2_9_52_1","article-title":"Big Data, Traditional Data and the Tradeoffs Between Prediction and Causality in Highway Safety Analysis","volume":"29","author":"Mannering F.","year":"2021","journal-title":"Analytic Methods in Accident Research"},{"key":"e_1_2_9_53_1","first-page":"1727","article-title":"Neural Variational Inference for Text Processing","volume":"48","author":"Miao Y.","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"key":"e_1_2_9_54_1","first-page":"411","article-title":"Topic Models Conditioned on Arbitrary Features Wwith Dirichlet\u2010Multinomial Regression","volume":"7","author":"Mimno D.","year":"2008","journal-title":"Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1177\/0361198119845899"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11524-017-0222-6"},{"key":"e_1_2_9_57_1","volume-title":"Probabilistic Machine Learning: An Introduction","author":"Murphy K.","year":"2022"},{"key":"e_1_2_9_58_1","first-page":"12","article-title":"Analysis of Injury Severity in Urban Road Crashes Involving Vulnerable Road Users Using Artificial Neural Networks","volume":"103","author":"Mussone L.","year":"2017","journal-title":"Accident Analysis & Prevention"},{"key":"e_1_2_9_59_1","doi-asserted-by":"publisher","DOI":"10.1080\/13588265.2020.1718465"},{"key":"e_1_2_9_60_1","unstructured":"National Highway Transportation Safety Administration.2010. \u201cCrash Factors in Intersection\u2010Related Crashes: An On\u2010Scene Perspective.\u201d Technical Report."},{"key":"e_1_2_9_61_1","doi-asserted-by":"publisher","DOI":"10.47869\/tcsj.73.4.8"},{"key":"e_1_2_9_62_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trf.2015.07.024"},{"key":"e_1_2_9_63_1","first-page":"27730","article-title":"Training Language Models to Follow Instructions With Human Feedback","volume":"35","author":"Ouyang L.","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_64_1","first-page":"1","article-title":"Injury Severity of Bus\u2010Pedestrian Crashes in South Korea Considering the Effects of Regional and Company Factors","volume":"11","author":"Park H. C.","year":"2019","journal-title":"Sustainability"},{"key":"e_1_2_9_65_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12544-013-0107-z"},{"key":"e_1_2_9_66_1","doi-asserted-by":"publisher","DOI":"10.3141\/2265-02"},{"key":"e_1_2_9_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_2_9_68_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2016.1141684"},{"key":"e_1_2_9_69_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v091.i02"},{"key":"e_1_2_9_70_1","doi-asserted-by":"publisher","DOI":"10.1111\/ajps.12103"},{"key":"e_1_2_9_71_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2018.07.008"},{"key":"e_1_2_9_72_1","first-page":"1","article-title":"Assessment of Traffic Accident Injury Severity Using Artificial Neural Networks and Random Forest Models","volume":"104","author":"Sameen M. I.","year":"2017","journal-title":"Transportation Research Part A: Policy and Practice"},{"key":"e_1_2_9_73_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.retrec.2012.12.011"},{"key":"e_1_2_9_74_1","doi-asserted-by":"publisher","DOI":"10.1080\/19439962.2021.1941460"},{"key":"e_1_2_9_75_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jtte.2020.07.004"},{"issue":"3","key":"e_1_2_9_76_1","article-title":"Road Crash Analysis and Modeling: A Systematic Review of Methods, Data, and Emerging Technologies","volume":"15","author":"Skaug L.","year":"2025","journal-title":"Applied Sciences"},{"key":"e_1_2_9_77_1","unstructured":"Srivastava A. andC.Sutton.2017. \u201cAutoencoding Variational Inference for Topic Models.\u201dInternational Conference on Learning Representations."},{"key":"e_1_2_9_78_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2020.105736"},{"key":"e_1_2_9_79_1","doi-asserted-by":"publisher","DOI":"10.1080\/15389588.2012.661110"},{"key":"e_1_2_9_80_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.leaqua.2021.101576"},{"key":"e_1_2_9_81_1","unstructured":"United Nations.2022. \u201cIntelligent Transport Systems for Sustainable Mobility.\u201d Technical Report."},{"key":"e_1_2_9_82_1","unstructured":"United Nations Economic Commission for Europe.2015. \u201cSustainable Urban Mobility and Public Transport in UNECE Capitals.\u201d Technical Report."},{"key":"e_1_2_9_83_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2023.107323"},{"key":"e_1_2_9_84_1","doi-asserted-by":"publisher","DOI":"10.1111\/risa.17708"},{"key":"e_1_2_9_85_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2016.09.014"},{"key":"e_1_2_9_86_1","doi-asserted-by":"publisher","DOI":"10.1080\/01441647.2021.1954108"},{"key":"e_1_2_9_87_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1539-6924.2012.01879.x"},{"key":"e_1_2_9_88_1","doi-asserted-by":"publisher","DOI":"10.1177\/0018720821989511"},{"key":"e_1_2_9_89_1","unstructured":"World Health Organization.2023. \u201cGlobal Status Report on Road Safety.\u201d Technical Report."},{"key":"e_1_2_9_90_1","article-title":"Crash Injury Severity Analysis Using Rough Set Theory and Support Vector Machine","volume":"132","author":"Xi Y.","year":"2019","journal-title":"Accident Analysis & Prevention"},{"key":"e_1_2_9_91_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2014.10.020"},{"key":"e_1_2_9_92_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aap.2006.12.006"},{"key":"e_1_2_9_93_1","doi-asserted-by":"publisher","DOI":"10.1080\/13588265.2019.1687152"},{"key":"e_1_2_9_94_1","doi-asserted-by":"publisher","DOI":"10.3141\/2647-01"},{"key":"e_1_2_9_95_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iatssr.2018.02.001"},{"key":"e_1_2_9_96_1","first-page":"211","article-title":"Analyzing Injury Severity of Rear\u2010End Crashes Involving Distracted Drivers Using Random Parameter Logit Models With Heterogeneity in Means and Variances","volume":"125","author":"Zeng Q.","year":"2019","journal-title":"Accident Analysis & Prevention"},{"key":"e_1_2_9_97_1","doi-asserted-by":"publisher","DOI":"10.1080\/17457300.2024.2440939"},{"key":"e_1_2_9_98_1","first-page":"1059","article-title":"The Huge Package for High\u2010Dimensional Undirected Graph Estimation in R","volume":"13","author":"Zhao T.","year":"2012","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_9_99_1","first-page":"182","article-title":"Modeling Injury Severity of Traffic Crashes With Heterogeneous Data: An Artificial Neural Network Approach","volume":"125","author":"Zheng Z.","year":"2019","journal-title":"Accident Analysis & Prevention"},{"key":"e_1_2_9_100_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e39959"}],"container-title":["Risk Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/risa.70183","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/risa.70183","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/risa.70183","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,15]],"date-time":"2026-02-15T07:13:35Z","timestamp":1771139615000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/risa.70183"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":99,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["10.1111\/risa.70183"],"URL":"https:\/\/doi.org\/10.1111\/risa.70183","archive":["Portico"],"relation":{},"ISSN":["0272-4332","1539-6924"],"issn-type":[{"value":"0272-4332","type":"print"},{"value":"1539-6924","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-12-31","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70183"}}