Early Prediction in Large-scale Time-variant Information Networks

本计画旨在发展一个早期预测系统，以预测时变资讯网路中可能爆发的恶意讯息。该研究将主要利用大规模社交网络中时变子序列和子结构模式的深度表示，在恶意和恶意消息有机会传播之前发出信号。该项目将为这一新兴领域奠定理论基础，以加强澳大利亚在数据科学领域的世界领导地位。实际上，开发的新理论和数据分析技术将有助于保护澳大利亚的商业，工业和社会免受网络欺诈，在线谣言传播和财务损失。

This project aims to develop an early prediction system to predict possible outbreaks of malicious messages in time-variant information networks. The research will primarily leverage deep representations of time-variant subsequence and substructure patterns in large-scale social networks to signal malicious and malevolent messages before it has a chance to propagate. This project will lay the theoretical foundations of this emerging field to strengthen Australia’s world leadership role in data science. Practically, the novel theories and data analytics technologies developed will help to safeguard Australian business, industry, and society from cyberfraud, online rumour-mongering, and financial loss.