Automated Classification of Criminal and Violent Activities in Thailand from Online News Articles

Abstract

Criminal and violent activities are a universal concern that affects a society's nature of life and economic dynamics. With dramatically increasing crime rates, law enforcement agencies have begun to show attention in utilizing machine learning approaches to analyze crime patterns to protect their communities. However, there are only a few studies that carried out experiments to classify Thai crime news articles into their proper categories. Also, the comparison of various machine learning algorithms toward this task has still been under-investigated. Therefore, in this paper, we aim to develop a framework to automate the classification and visualization of criminal and violent activities from online Thai news articles. Six classifiers are employed to classify crime news articles into one of the five crime categories including Burglary, Drug, Murder, Accident, and Corruption. The results have shown that Support Vector Machine and Logistic Regression approaches outperform other classifiers in terms of Accuracy, Precision, Recall, and F-Measure metrics.