Development of Massive Data Analytics for Rumor Source Detection and Faked News Invalidation against Infodemic
(PI: Prof Chee Wei Tan; Co-I: Prof Guanrong Chen)

Publications

C. N. Hang, P. -D. Yu, S. Chen, C. W. Tan and G. Chen, "MEGA: Machine Learning-Enhanced Graph Analytics for Infodemic Risk Management," in IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 12, pp. 6100-6111, Dec. 2023, doi: 10.1109/JBHI.2023.3314632.

C. W. Tan and P. -D. Yu, "Contagion Source Detection in Epidemic and Infodemic Outbreaks: Mathematical Analysis and Network Algorithms," in Foundations and Trends® in Networking, vol. 13, no. 2-3, pp. 107-251, Jul. 2023, http://dx.doi.org/10.1561/1300000068

Table of Contents

1. Chapter 1: Network Centrality
2. Chapter 2: Digital Contact Tracing - Source Detection Simulator
3. Chapter 3: Distance-based Source Estimator
4. Chapter 4: Novel Framework
5. Chapter 5: Limitations
6. Chapter 6: Comprehensive Report

The above table links to a set of interactive notebooks for learning network science for source detection.

Objectives

The objectives of this project could be summarized as follows:

• To provide an organized compendium of interactive notebooks that serve as educational resources on network science, specifically tailored towards rumor source detection for infodemic risk management.
• To introduce the concept of network centrality and its application in understanding the dynamics of information spread within networks.
• To demonstrate the use of digital contact tracing as a means for source detection through a simulator that can model the spread of information.
• To present the distance-based source estimator as an analytical tool for identifying the origins of information spread in a network.
• To discuss the limitations inherent in the current methods and models of source detection and faked news invalidation, opening a dialogue for improvement and further research.
• To facilitate a hands-on learning experience for users, enabling them to interact with and manipulate network data for better comprehension of the methodologies discussed.
• To contribute to the global effort against misinformation by equipping researchers, practitioners, and students with the necessary analytical skills to tackle the infodemic.