A framework based on Natural Language Processing and Machine Learning for the classification of the severity of road accidents from reports

Abstract

Road safety analysis is typically performed by domain experts on the basis of the information contained in accident reports. The main challenges are the difficulty of considering a large number of reports in textual form and the subjectivity of the expert judgments contained in reports. This work develops a framework based on the combination of Natural Language Processing (NLP) and Machine Learning (ML) for the automatic classification of accidents with the final aim of assisting experts in performing road safety analyses. Two different models for the representation of the textual reports (Hierarchical Dirichlet Processes (HDPs) and Doc2vec) and three ML-based classifiers (Artificial Neural Networks (ANNs), Decision Trees (DTs) and Random Forests (RFs)) are compared. The framework is applied to a repository of road accident reports provided by the US National Highway Traffic Safety Administration. The best trade-off between accuracy of the classification and explainability of the obtained results is achieved by combining HDP topic modeling and RF classification.

Predicting the Type of Road Traffic Accident for Test Scenario Generation

“…Thus, 1AT contains only seven different classes to be predicted, which are significantly fewer than 3AT, consisting of 297 different accident types to be predicted [10]. Furthermore, other research on building classifiers based on police accident data often focuses on predicting or modelling injury-related parameters, for example, the accident severity or the number of injured people [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], [29], or investigating risk factors [30], [31], [32], [33], [34], [35], [36]. Additionally, models regarding crash type, typically describing how road users hit each other, 1 seem to be part of the research focus [37], [38], [39], [40], [41].…”

Highway Construction Safety Analysis Using Large Language Models

“…It is important to recognize that work zone characteristics and the environment exert a significant influence on work zone accidents, injuries, and fatalities [7]. Additionally, human factors, such as worker behavior and ergonomics, play a crucial role in accidents in highway construction zones [1,6].…”

“…Various approaches have been explored, including combining Term Frequency-Inverse Document Frequency (TFIDF) with machine learning classifiers, utilizing the K-means clustering algorithm for data mining and employing feature analysis through descriptive statistics [9]. TFIDF, a traditional method in text analytics, quantifies words' importance in a document, but it has limitations in capturing word similarity and accurately reflecting their importance [7].…”