TransCrimeNet: A Transformer-Based Model for Text-Based Crime Prediction in Criminal Networks

TL;DR

TransCrimeNet introduces a transformer-based approach that combines textual data and graph embeddings to improve crime prediction accuracy in criminal networks, outperforming previous models significantly.

Contribution

The paper proposes TransCrimeNet, a novel model integrating transformer-derived textual features with graph data for enhanced crime prediction in criminal networks.

Findings

TransCrimeNet achieves 12.7% higher F1 score than previous models.

Combining textual and graph data improves prediction accuracy.

Transformer-based features effectively capture valuable insights from unstructured text.

Abstract

This paper presents TransCrimeNet, a novel transformer-based model for predicting future crimes in criminal networks from textual data. Criminal network analysis has become vital for law enforcement agencies to prevent crimes. However, existing graph-based methods fail to effectively incorporate crucial textual data like social media posts and interrogation transcripts that provide valuable insights into planned criminal activities. To address this limitation, we develop TransCrimeNet which leverages the representation learning capabilities of transformer models like BERT to extract features from unstructured text data. These text-derived features are fused with graph embeddings of the criminal network for accurate prediction of future crimes. Extensive experiments on real-world criminal network datasets demonstrate that TransCrimeNet outperforms previous state-of-the-art models by 12.7\% in F1 score for crime prediction. The results showcase the benefits of combining textual and graph-based features for actionable insights to disrupt criminal enterprises.