A Multifaceted Machine Learning Approach to Understand Road Accident Dynamics Using Twitter Data

Abstract

Road accidents, causing 1.35 billion deaths and 50 million injuries annually, are a significant global issue that demands timely detection and prevention. This study reviews existing research on road accident detection using data mining techniques. In this research, the authors developed a method for classifying road accident-related tweets using Twitter mining. They collected a dataset of road accident-related tweets, pre-processed them, and cleaned the data using natural language processing. Various machine learning models were applied to classify tweets into real-time, traffic, and informative categories, including SVM, logistic regression, ANN, LSTM with TF-IDF, and LSTM with BERT. The LSTM model with BERT exhibited the highest precision and recall scores of 0.88 and 0.87, respectively. The findings highlight the potential of Twitter mining for real-time road accident detection. Despite model accuracy and robustness limitations, this research is a promising starting point for leveraging social media data to enhance road safety.