Detecting crime intent from user-generated content on social media platforms has become increasingly important for law enforcement and crime prevention. This paper presents a comprehensive approach for crime intent detection from user tweets using machine learning techniques. The study utilizes a dataset of about 400,000 tweets and applies data preprocessing, feature selection, and model training with logistic regression, ridge regression classifier, Stochastic Gradient Descent (SGD) classifier, Random Forests, and support vector machine models. Evaluation metrics such as accuracy, precision, recall, and F1 score are employed to assess the models’ performance. The results reveal that the logistic regression model achieves the highest accuracy ratio of 0.981 in detecting crime intent from tweets. This research showcases the effectiveness of machine learning and advanced transformer-based models in leveraging social media data for crime analysis. The findings provide valuable insights into the potential for early detection and monitoring of crime intent using online platforms, contributing to the field of crime prevention and law enforcement. The utilization of machine learning techniques offers new avenues for understanding and analyzing crime-related sentiments expressed by social media users. By accurately detecting crime intent from user-generated content, law enforcement agencies can enhance their proactive measures, monitor public sentiment towards crime, and shape policies and interventions to address public concerns effectively. The research highlights the significance of leveraging social media data for crime detection and emphasizes the potential impact of advanced machine learning models in improving public safety and crime prevention efforts.