Crime-Intent Sentiment Detection on Twitter Data Using Machine Learning

Abstract

This research examines sentiment analysis in the context of crime intent using machine learning algorithms. A comparison is made between a crime intent dataset generated from a Twitter developer account and Kaggle's sentiment140 dataset for Twitter sentiment analysis. The algorithms employed include Support Vector Machine (SVM), Naïve Bayes, and Long Short-Term Memory (LSTM). The findings indicate that LSTM outperforms the other algorithms, achieving high accuracy (97%) and precision (99%) in detecting crime tweets. Thus, it is concluded that the crime tweets were accurately identified.