[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121091-en":3,"doc-seo-121091-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},121091,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Enhancing Traffic Incident Management with Large Language Models - A Hybrid Machine Learning Approach for Severity Classification","This research integrates Large Language Models into machine learning workflows for traffic incident management, targeting accident severity classification from incident reports. It combines language-model-generated features with conventional features extracted from reports, improving accuracy across multiple machine learning algorithms. The study provides a comprehensive comparison of model combinations using several large language models for feature extraction, evaluates language-enhanced feature engineering against traditional pipelines for unstructured text, and demonstrates that fusing baseline report features with language-based features increases classification accuracy. Applied to datasets from the US, UK, and Queensland, Australia, the approach supports robust cross-domain adoption.","Enhancing Traffic Incident Management with Large Language Models: A Hybrid Machine Learning Approach for Severity Classification*  \narXiv :2403 . 13547v2 [ cs .LG] 29 Apr 2024  \n1st Artur Grigorev Faculty of Engineering and IT University of Technology Sydney Sydney, Australia ORCID: 0000-0001-6875-3568 [Artur.Grigorev@uts.edu.au](Artur.Grigorev@uts.edu.au)  \n2rd Khaled Saleh Faculty of Engineering and IT University of Newcastle Newcastle, Australia ORCID: 0000-0002-2589-179X[Khaled.Saleh@newcastle.edu.au](Khaled.Saleh@newcastle.edu.au)  \n3th Yuming Ou Faculty of Engineering and IT University of Technology Sydney Sydney, Australia ORCID: 0000-0001-5922-9406 [Yuming.Ou@uts.edu.au](Yuming.Ou@uts.edu.au)  \n4nd Adriana-Simona Mihit¸  \nFaculty of Engineering and IT University of Technology Sydney  \nSydney, Australia ORCID: 0000-0001-7670-5777 [Adriana-Simona.Mihaita@uts.edu.au](Adriana-Simona.Mihaita@uts.edu.au)  \nI. ABSTRACT  \nThis research showcases the innovative integration of Large Language Models into machine learning workflows for traffic incident management, focusing on the classification of incident severity using accident reports. By leveraging features generated by modern language models alongside conventional data extracted from incident reports, our research demonstrates improvements in the accuracy of severity classification across several machine learning algorithms. Our contributions are threefold. First, we present an extensive comparison of various machine learning models paired with multiple large language models for feature extraction, aiming to identify the optimal combinations for accurate incident severity classification. Second, we contrast traditional feature engineering pipelines with those enhanced by language models, showcasing the superiority of language-based feature engineering in processing unstructured text. Third, our study illustrates how merging baseline features from accident reports with language-based features can improve the severity classification accuracy. This comprehensive approach not only advances the field of incident management but also highlights the cross-domain application potential of our methodology, particularly in contexts requiring the prediction of event outcomes from unstructured textual data or features translated into textual representation. Specifically, our novel methodology was applied to three distinct datasets originating from the United States, the United Kingdom, and Queensland, Australia. This cross-continental application underlines the robustness of our approach, suggesting its potential for widespread adoption in improving incident management processes globally.  \nKeywords: traffic accident, incident severity classification, machine learning, traffic management, large language models  \nII. INTRODUCTION  \nThe rise in vehicular traffic over the past few decades has led to a corresponding increase in traffic accidents, with over five million reported in the United States in 2013 alone according to the National Highway Traffic Safety Administration (NHTSA)  \n[1] . This surge underscores the need for effective Traffic Incident Management Systems (TIMS) capable of handling complex datasets involving accident details, traffic conditions, and environmental factors.  \nA critical aspect of TIMS is the ability to classify the traffic accident severity accurately, which is essential in determining the resources required for response - including team size, equipment, and traffic control measures [2] . However, classifying accident severity poses significant challenges due to the stochastic nature of traffic accidents [3] . Therefore, it’s necessary to perform the research in the direction of finding more efficient models.  \nThe ability of LLMs to understand and process unstructured textual data from incident reports presents a significant opportunity to augment conventional machine learning approaches. These algorithms have typically been applied to structured tabular data, b","cbCaichN6ueaeF8P","https://ap.wps.com/l/cbCaichN6ueaeF8P","pdf",566814,1,17,"English","en",105,"# Abstract\n# Introduction\n## Traffic Incident Management Systems and Severity Classification\n## Role of Large Language Models in Unstructured Text","[{\"question\":\"How does the proposed method use large language models for severity classification?\",\"answer\":\"It extracts features from accident report text using large language models, then combines them with conventional features derived from incident reports to classify severity.\"},{\"question\":\"What comparisons does the research conduct?\",\"answer\":\"It compares combinations of various machine learning models paired with multiple large language models for feature extraction, and contrasts traditional feature engineering pipelines with language-model-enhanced ones.\"},{\"question\":\"Why is the hybrid feature strategy expected to improve performance?\",\"answer\":\"Fusing baseline features from accident reports with language-based features leverages both structured information and unstructured textual cues, improving severity classification accuracy.\"}]","Enhancing Traffic Incident Management with Large Language Models - A Hybrid Machine Learning Approach for Severity Classification | PDF",1785733674,43,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"enhancing-traffic-incident-management-with-large-language-models-a-hybrid-machine-learning-approach-for-severity-classification","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/enhancing-traffic-incident-management-with-large-language-models-a-hybrid-machine-learning-approach-for-severity-classification/121091/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"How does the proposed method use large language models for severity classification?","Question",{"text":75,"@type":76},"It extracts features from accident report text using large language models, then combines them with conventional features derived from incident reports to classify severity.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What comparisons does the research conduct?",{"text":80,"@type":76},"It compares combinations of various machine learning models paired with multiple large language models for feature extraction, and contrasts traditional feature engineering pipelines with language-model-enhanced ones.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is the hybrid feature strategy expected to improve performance?",{"text":84,"@type":76},"Fusing baseline features from accident reports with language-based features leverages both structured information and unstructured textual cues, improving severity classification accuracy.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]