This study explores traffic crash narratives in an attempt to inform and enhance effective traffic safety policies using text-mining analytics. Text mining techniques are employed to unravel key themes and trends within the narratives, aiming to provide a deeper understanding of the factors contributing to traffic crashes. This study collected crash data from five major freeways in Jordan that cover narratives of 7,587 records from 2018-2022. An unsupervised learning method was adopted to learn the pattern from crash data. Various text mining techniques, such as topic modeling, keyword extraction, and Word Co-Occurrence Network, were also used to reveal the co-occurrence of crash patterns. Results show that text mining analytics is a promising method and underscore the multifactorial nature of traffic crashes, including intertwining human decisions and vehicular conditions. The recurrent themes across all analyses highlight the need for a balanced approach to road safety, merging both proactive and reactive measures. Emphasis on driver education and awareness around animal-related incidents is paramount.
@article{arxiv.2406.09438,
title = {Exploring Traffic Crash Narratives in Jordan Using Text Mining Analytics},
author = {Shadi Jaradat and Taqwa I. Alhadidi and Huthaifa I. Ashqar and Ahmed Hossain and Mohammed Elhenawy},
journal= {arXiv preprint arXiv:2406.09438},
year = {2024}
}