{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T01:13:23Z","timestamp":1792026803365,"version":"4.4.0"},"reference-count":39,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,2,1]],"date-time":"2025-02-01T00:00:00Z","timestamp":1738368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Safety Research"],"published-print":{"date-parts":[[2025,2]]},"DOI":"10.1016\/j.jsr.2024.11.009","type":"journal-article","created":{"date-parts":[[2024,11,13]],"date-time":"2024-11-13T17:56:41Z","timestamp":1731520601000},"page":"1-13","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":35,"special_numbering":"C","title":["A large language model framework to uncover underreporting in traffic crashes"],"prefix":"10.1016","volume":"92","author":[{"given":"Cristian","family":"Arteaga","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"JeeWoong","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jsr.2024.11.009_b0005","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.aap.2017.07.018","article-title":"Errors in accident data, its types, causes and methods of rectification-analysis of the literature","volume":"130","author":"Ahmed","year":"2019","journal-title":"Accid Anal Prev"},{"key":"10.1016\/j.jsr.2024.11.009_b0010","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1016\/S0001-4575(00)00049-X","article-title":"Under-reporting of motor vehicle traffic crash victims in New Zealand","volume":"33","author":"Alsop","year":"2001","journal-title":"Accid Anal Prev"},{"key":"10.1016\/j.jsr.2024.11.009_b0015","series-title":"Relationship between unsignalised intersection geometry and accident rates","author":"Arndt","year":"2003"},{"key":"10.1016\/j.jsr.2024.11.009_b0020","doi-asserted-by":"crossref","unstructured":"Arteaga, C., Park, J., 2023. Deep Learning and Clustering-Based Analysis of Text Narratives for Identification of Traffic Crash Severity Contributors, in: MAIREINFRA 2023. MDPI, Basel Switzerland, p. 31. https:\/\/doi.org\/10.3390\/engproc2023036031.","DOI":"10.3390\/engproc2023036031"},{"key":"10.1016\/j.jsr.2024.11.009_b0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.jocm.2021.100339","article-title":"xlogit: An open-source Python package for GPU-accelerated estimation of Mixed Logit models","volume":"42","author":"Arteaga","year":"2022","journal-title":"Journal of Choice Modelling"},{"key":"10.1016\/j.jsr.2024.11.009_b0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.ssci.2020.104988","article-title":"Injury severity on traffic crashes: A text mining with an interpretable machine-learning approach","volume":"132","author":"Arteaga","year":"2020","journal-title":"Saf Sci"},{"key":"10.1016\/j.jsr.2024.11.009_b0035","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/0001-4575(94)00065-T","article-title":"The identification of mistakes in road accident records: Part 1, locational variables","volume":"27","author":"Austin","year":"1995","journal-title":"Accid Anal Prev"},{"key":"10.1016\/j.jsr.2024.11.009_b0040","doi-asserted-by":"crossref","unstructured":"Beltagy, I., Lo, K., Cohan, A., 2019. SciBERT: A Pretrained Language Model for Scientific Text.","DOI":"10.18653\/v1\/D19-1371"},{"key":"10.1016\/j.jsr.2024.11.009_b0045","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1080\/15389588.2012.655431","article-title":"Challenges in Evaluating the Decade of Action for Road Safety in Developing Countries: A Survey of Traffic Fatality Reporting Capacity in the Eastern Mediterranean Region","volume":"13","author":"Bhatti","year":"2012","journal-title":"Traffic Inj Prev"},{"key":"10.1016\/j.jsr.2024.11.009_b0050","unstructured":"Brown, T.B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R., Ramesh, A., Ziegler, D.M., Wu, J., Winter, C., Hesse, C., Chen, M., Sigler, E., Litwin, M., Gray, S., Chess, B., Clark, J., Berner, C., McCandlish, S., Radford, A., Sutskever, I., Amodei, D., 2020. Language Models are Few-Shot Learners."},{"key":"10.1016\/j.jsr.2024.11.009_b0055","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.ijtst.2018.10.001","article-title":"A multinomial logit model of pedestrian-vehicle crash severity in North Carolina","volume":"8","author":"Chen","year":"2019","journal-title":"International Journal of Transportation Science and Technology"},{"key":"10.1016\/j.jsr.2024.11.009_b0060","doi-asserted-by":"crossref","first-page":"877","DOI":"10.1080\/13811118.2023.2247026","article-title":"Unlocking the narrative: Using text mining to reveal the hidden factors behind suicide related traffic crashes","volume":"28","author":"Das","year":"2024","journal-title":"Archives of Suicide Research"},{"key":"10.1016\/j.jsr.2024.11.009_b0065","series-title":"in: Transportation Research Board 102nd Annual Meeting","article-title":"Crash contributing factors and patterns associated with fatal truck-involved crashes in Bangladesh: Findings from text mining approach","author":"Hossain","year":"2023"},{"key":"10.1016\/j.jsr.2024.11.009_b0070","article-title":"Application of text mining techniques to identify actual wrong-way driving (WWD) crashes in police reports","author":"Hosseini","year":"2022","journal-title":"International Journal of Transportation Science and Technology"},{"key":"10.1016\/j.jsr.2024.11.009_b0075","unstructured":"ITF, 2017. Alcohol-Related Road Casualties in Official Crash Statistics."},{"key":"10.1016\/j.jsr.2024.11.009_b0080","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1080\/15389588.2015.1128533","article-title":"Understanding traffic crash under-reporting: Linking police and medical records to individual and crash characteristics","volume":"17","author":"Janstrup","year":"2016","journal-title":"Traffic Inj Prev"},{"key":"10.1016\/j.jsr.2024.11.009_b0085","unstructured":"Khattab, O., Singhvi, A., Maheshwari, P., Zhang, Z., Santhanam, K., Vardhamanan, S., Haq, S., Sharma, A., Joshi, T.T., Moazam, H., Miller, H., Zaharia, M., Potts, C., 2023. DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines."},{"key":"10.1016\/j.jsr.2024.11.009_b0090","doi-asserted-by":"crossref","first-page":"1751","DOI":"10.1016\/j.aap.2010.04.016","article-title":"A note on modeling pedestrian-injury severity in motor-vehicle crashes with the mixed logit model","volume":"42","author":"Kim","year":"2010","journal-title":"Accid Anal Prev"},{"key":"10.1016\/j.jsr.2024.11.009_b0095","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2021.106473","article-title":"Mining patterns of autonomous vehicle crashes involving vulnerable road users to understand the associated factors","volume":"165","author":"Kutela","year":"2022","journal-title":"Accid Anal Prev"},{"key":"10.1016\/j.jsr.2024.11.009_b0100","doi-asserted-by":"crossref","DOI":"10.55329\/fiqq8731","article-title":"Leveraging autonomous vehicles crash narratives to understand the patterns of parking-related crashes","volume":"4","author":"Kutela","year":"2023","journal-title":"Traffic Safety Research"},{"key":"10.1016\/j.jsr.2024.11.009_b0105","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4385895","article-title":"Uncovering the influence of ChatGPT\u2019s prompts on scientific writings using machine learning-based text mining approaches","author":"Kutela","year":"2023","journal-title":"SSRN Electronic Journal"},{"key":"10.1016\/j.jsr.2024.11.009_b0110","unstructured":"MassDOT, 2023. MassDOT IMPACT Crash Data Portal [WWW Document]. URL https:\/\/apps.impact.dot.state.ma.us\/cdp\/home (accessed 8.24.23)."},{"key":"10.1016\/j.jsr.2024.11.009_b0115","first-page":"87","article-title":"Underreporting of driver alcohol involvement in united states police and hospital records: Capture-recapture estimates","volume":"56","author":"Miller","year":"2012","journal-title":"Annals of Advances in Automotive Medicine \/ Annual Scientific Conference"},{"key":"10.1016\/j.jsr.2024.11.009_b0120","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1016\/j.aap.2007.06.006","article-title":"Highway accident severities and the mixed logit model: An exploratory empirical analysis","volume":"40","author":"Milton","year":"2008","journal-title":"Accid Anal Prev"},{"key":"10.1016\/j.jsr.2024.11.009_b0125","unstructured":"OpenAI, 2022. Introducing ChatGPT [WWW Document]. OpenAI Blog. URL https:\/\/openai.com\/blog\/chatgpt (accessed 8.11.23)."},{"key":"10.1016\/j.jsr.2024.11.009_b0130","unstructured":"Raffel, C., Shazeer, N., Roberts, A., Lee, K., Narang, S., Matena, M., Zhou, Y., Li, W., Liu, P.J., 2019. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer."},{"key":"10.1016\/j.jsr.2024.11.009_b0135","doi-asserted-by":"crossref","unstructured":"Rella Riccardi, M., Mauriello, F., Scarano, A., Montella, A., 2022. Analysis of contributory factors of fatal pedestrian crashes by mixed logit model and association rules. https:\/\/doi.org\/10.1080\/17457300.2022.2116647 30, 195\u2013209. https:\/\/doi.org\/10.1080\/17457300.2022.2116647.","DOI":"10.1080\/17457300.2022.2116647"},{"key":"10.1016\/j.jsr.2024.11.009_b0140","doi-asserted-by":"crossref","first-page":"1666","DOI":"10.1016\/j.aap.2011.03.025","article-title":"The statistical analysis of highway crash-injury severities: A review and assessment of methodological alternatives","volume":"43","author":"Savolainen","year":"2011","journal-title":"Accid Anal Prev"},{"key":"10.1016\/j.jsr.2024.11.009_b0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.aap.2021.106211","article-title":"Identification and analysis of misclassified work-zone crashes using text mining techniques","volume":"159","author":"Sayed","year":"2021","journal-title":"Accid Anal Prev"},{"key":"10.1016\/j.jsr.2024.11.009_b0150","unstructured":"Tay, Y., Dehghani, M., Tran, V.Q., Garcia, X., Wei, J., Wang, X., Chung, H.W., Shakeri, S., Bahri, D., Schuster, T., Zheng, H.S., Zhou, D., Houlsby, N., Metzler, D., 2022. UL2: Unifying Language Learning Paradigms."},{"key":"10.1016\/j.jsr.2024.11.009_b0155","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozi\u00e8re, B., Goyal, N., Hambro, E., Azhar, F., Rodriguez, A., Joulin, A., Grave, E., Lample, G., 2023a. LLaMA: Open and Efficient Foundation Language Models."},{"key":"10.1016\/j.jsr.2024.11.009_b0160","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., Bhosale, S., Bikel, D., Blecher, L., Ferrer, C.C., Chen, M., Cucurull, G., Esiobu, D., Fernandes, J., Fu, J., Fu, W., Fuller, B., Gao, C., Goswami, V., Goyal, N., Hartshorn, A., Hosseini, S., Hou, R., Inan, H., Kardas, M., Kerkez, V., Khabsa, M., Kloumann, I., Korenev, A., Koura, P.S., Lachaux, M.-A., Lavril, T., Lee, J., Liskovich, D., Lu, Y., Mao, Y., Martinet, X., Mihaylov, T., Mishra, P., Molybog, I., Nie, Y., Poulton, A., Reizenstein, J., Rungta, R., Saladi, K., Schelten, A., Silva, R., Smith, E.M., Subramanian, R., Tan, X.E., Tang, B., Taylor, R., Williams, A., Kuan, J.X., Xu, P., Yan, Z., Zarov, I., Zhang, Y., Fan, A., Kambadur, M., Narang, S., Rodriguez, A., Stojnic, R., Edunov, S., Scialom, T., 2023b. Llama 2: Open Foundation and Fine-Tuned Chat Models."},{"key":"10.1016\/j.jsr.2024.11.009_b0165","first-page":"15","article-title":"Recording of alcohol in official crash statistics: Underreporting and procedures to improve statistics","volume":"29","author":"Vissers","year":"2018","journal-title":"Journal of Road Safety"},{"key":"10.1016\/j.jsr.2024.11.009_b0170","unstructured":"Wei, J., Bosma, M., Zhao, V.Y., Guu, K., Yu, A.W., Lester, B., Du, N., Dai, A.M., Le, Q. V., 2021. Finetuned Language Models Are Zero-Shot Learners."},{"key":"10.1016\/j.jsr.2024.11.009_b0175","unstructured":"WHO, 2018a. Global Status Report on Road Safety 2018."},{"key":"10.1016\/j.jsr.2024.11.009_b0180","unstructured":"WHO, 2018b. Global status report on alcohol and health."},{"key":"10.1016\/j.jsr.2024.11.009_b0185","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","author":"Wolf","year":"2020"},{"key":"10.1016\/j.jsr.2024.11.009_b0190","doi-asserted-by":"crossref","first-page":"31","DOI":"10.3141\/2002-05","article-title":"Examining deficiencies in Florida pedestrian crash data","volume":"2002","author":"Wootton","year":"2007","journal-title":"Transportation Research Record: Journal of the Transportation Research Board"},{"key":"10.1016\/j.jsr.2024.11.009_b0195","doi-asserted-by":"crossref","unstructured":"Zhang, X., Green, E., Chen, M., (Reg) Souleyrette, R.R., 2019. Identifying secondary crashes using text mining techniques. Journal of Transportation Safety & Security 1\u201321. https:\/\/doi.org\/10.1080\/19439962.2019.1597795.","DOI":"10.1080\/19439962.2019.1597795"}],"container-title":["Journal of Safety Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0022437524001580?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0022437524001580?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T05:13:32Z","timestamp":1740114812000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0022437524001580"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2]]},"references-count":39,"alternative-id":["S0022437524001580"],"URL":"https:\/\/doi.org\/10.1016\/j.jsr.2024.11.009","relation":{},"ISSN":["0022-4375"],"issn-type":[{"value":"0022-4375","type":"print"}],"subject":[],"published":{"date-parts":[[2025,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A large language model framework to uncover underreporting in traffic crashes","name":"articletitle","label":"Article Title"},{"value":"Journal of Safety Research","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jsr.2024.11.009","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}]}}