A Text-mining approach for crime tweets in Saudi Arabia: From analysis to prediction

Abstract

Social networks have proven to be a massive hub for investigating contextual and individual behavior of people. Most recently micro-blogging sites like Twitter are indicating to researchers that their content can be aggregated and used to effectively predict forecast, and infer outcomes of real-world events. The crime-related tweets analysis research in Saudi Arabia set off with an ultimate goal of gathering a deeper understanding of what kinds of criminal weapons are people frequently talking about. In this paper, we aim at dealing with tweets mentioning different weapons, analyzing them to gather facts such as annual variation of percentage tweets mentioning different weapons, recognizing the impact of events such as the Covid-19 pandemic on crime social discussions. In the following step, we develop a number of classifiers to predict which weapon is mentioned in a tweet. In order to perform our tasks, the Python programming language is used in the majority of the cases.