Detection of Rumors and Their Sources in Social Networks: A Comprehensive Survey

TL;DR

This survey addresses three interconnected problems in social networks: rumor-detection, rumor-source-detection, and their joint detection. It formalizes problem statements, surveys a wide range of detection algorithms across content-, propagation-, source-based, and hybrid paradigms, and discusses single- and multi-source source localization under various snapshot regimes. It also covers the complementary topics of hiding rumors and their sources and provides a comprehensive discussion of challenges, including data scale, temporal dynamics, cross-platform propagation, and ethical considerations, along with suggested directions for future work. The work highlights the practical significance of jointly inferring rumors and their origins to improve information integrity, counter misinformation, and enable targeted interventions while balancing privacy and platform-specific constraints.

Abstract

With the recent advancements in social network platform technology, an overwhelming amount of information is spreading rapidly. In this situation, it can become increasingly difficult to discern what information is false or true. If false information proliferates significantly, it can lead to undesirable outcomes. Hence, when we receive some information, we can pose the following two questions: $(i)$ Is the information true? $(ii)$ If not, who initially spread that information? % The first problem is the rumor detection issue, while the second is the rumor source detection problem. A rumor-detection problem involves identifying and mitigating false or misleading information spread via various communication channels, particularly online platforms and social media. Rumors can range from harmless ones to deliberately misleading content aimed at deceiving or manipulating audiences. Detecting misinformation is crucial for maintaining the integrity of information ecosystems and preventing harmful effects such as the spread of false beliefs, polarization, and even societal harm. Therefore, it is very important to quickly distinguish such misinformation while simultaneously finding its source to block it from spreading on the network. However, most of the existing surveys have analyzed these two issues separately. In this work, we first survey the existing research on the rumor-detection and rumor source detection problems with joint detection approaches, simultaneously. % This survey deals with these two issues together so that their relationship can be observed and it provides how the two problems are similar and different. The limitations arising from the rumor detection, rumor source detection, and their combination problems are also explained, and some challenges to be addressed in future works are presented.

Figures (4)

• Figure 1: Three main problems considered in this survey---rumor detection, rumor-source detection, and joint detection of rumor and rumor source in social networks. Here, "Infected node" is the node that heard the rumor from its neighbors.
• Figure 2: Example of propagation snapshot. A complete snapshot means that the entire spread of the rumor can be observed. A partial snapshot means that the infection status is partially hidden when a rumor spreads. Sensor-monitoring snapshot refers to installing sensors in some nodes in the network to observe the spread of rumors.
• Figure 3: Examples of Estimators. The estimator on the left is the Jordan center, one of the graph-based estimators. The estimator on the right is the MLE, one of the probabilistic estimators. While the graph-based estimator estimates the center node by analyzing the snapshots of all rumors, the probabilistic estimator calculates the probability for the sample path of the infection route and selects the node with the maximum.
• Figure 4: A hide-and-seek game of rumor sources Luo16. In the game, one player uses a strategy to control the rumor propagation rate at each edge to hide the rumor source. To find the source of the rumor in such a situation, another player establishes an estimation set centered on the well-known Jordan Center (JC) and allows the source to enter it.

Theorems & Definitions (5)

• Definition 1
• Definition 2
• Definition 3
• Definition 4
• Definition 5