AI-Crime Hunter: An AI Mixture of Experts for Crime Discovery on Twitter

Abstract

Maintaining a healthy cyber society is a great challenge due to the users’ freedom of expression and behavior. This can be solved by monitoring and analyzing the users’ behavior and taking proper actions. This research aims to present a platform that monitors the public content on Twitter by extracting tweet data. After maintaining the data, the users’ interactions are analyzed using graph analysis methods. Then, the users’ behavioral patterns are analyzed by applying metadata analysis, in which the timeline of each profile is obtained; also, the time-series behavioral features of users are investigated. Then, in the abnormal behavior detection and filtering component, the interesting profiles are selected for further examinations. Finally, in the contextual analysis component, the contents are analyzed using natural language processing techniques; a binary text classification model (SVM (Support Vector Machine) + TF-IDF (Term Frequency—Inverse Document Frequency) with 88.89% accuracy) is used to detect if a tweet is related to crime or not. Then, a sentiment analysis method is applied to the crime-related tweets to perform aspect-based sentiment analysis (DistilBERT + FFNN (Feed-Forward Neural Network) with 80% accuracy), because sharing positive opinions about a crime-related topic can threaten society. This platform aims to provide the end-user (the police) with suggestions to control hate speech or terrorist propaganda.

Analysis of social networks and filtering of Arabic crime tweets based on an intelligent dictionary using a genetic algorithm

“…The paper [16] used dynamic time-warping to analyze profiles of users, focusing on behavioral habits, audience, and shared content, and determining similarity using the TF-IDF and cosine similarity metrics. This study [17] analyzes tweet data to create a Twitter monitoring tool. Graph analysis examines user behavior following data maintenance.…”

“…Popular measures of central tendency include degree, proximity, betweenness, eigenvector, and page rank A concise explanation of these measures is provided below [17].…”

A Systematic Review on the use of Machine Learning and Deep Learning Techniques for Crime Prediction from Social Media

“…To construct an AI model for the crime discovery rate prediction using the twitter data [30]. The user interactions and behavioral patterns were determined by using the graph analysis and meta-data methods from which the timeline of each profile and time-series behavioral features of users.…”

Artificial Intelligence in Engineering and Computer Science Learning: Systematic Review Article

“…In addition, that the A.I. is part of cybersecurity resources and for this it has a large database or metadata found in social networks, where users' behaviors and reactions to advertisements or images that appear frequently are stored according to their information search, it means that users have started to see or search within social networks or web pages (Shoeibi et al, 2021), these become frequent or part of the content related to the initial search, this is where cyber security comes into play for all those seeking protection of all kinds from advertisements and scams, engineering is in constant development by the existence of hackers or engineers with evil intentions.…”