Zelin Zhang

Rumor blocking approaches in social networks aim to identify a small set of counter-rumor seed nodes and compete with rumor cascades to quickly stop the propagation of rumors. However, current rumor blocking methods assume complete knowledge of rumor node positions, which is often unattainable in real-world scenarios. In this paper, we introduce the concept of Uncertainty Rumor Blocking, where we address the uncertainty surrounding rumor node locations by considering a set of suspicious nodes, each associated with a probability indicating the likelihood of rumor propagation. As traditional node selection algorithms become inadequate under uncertain conditions, we propose a Graph Neural Network-based Inverse Reinforcement Learning (G-IRL) approach to effectively select counter-rumor seed nodes. Through comprehensive experimentation on three datasets, we demonstrate the consistent superiority of our G-IRL over state-of-the-art baseline methods for node selection in the context of uncertainty rumor containment.

The rumor blocking approaches in social networks aim to identify a small set of counter-rumor seed nodes to quickly stop the propagation of rumors. Existing solutions predominantly focus on minimizing the influence of rumor propagation (i.e., the number of affected nodes), while treating transmission time as a constraint rather than an optimization objective, despite its critical importance in real-world scenarios. In this view, we firstly elaborate on a multi-objective rumor blocking optimization problem, which strives to simultaneously minimize the influence of rumor propagation and the transmission time, that is, to stop the rumor propagation in the shortest possible time. Then, we further propose a Continuous-Time Competitive Cascading (CTCC) model, which, adapted from the independent cascading model, introduces the concept of transmission time and the competitions between nodes, and characterizes the influence process of different nodes as a continuous process. Besides, to tackle the multi-objective rumor blocking problem, we design a Reinforcement Learning approach with Graph Convolution network (denoted as RLGC) to effectively select counter-rumor seed nodes. Extensive experimental results on three real datasets validate that RLGC can consistently perform better than representative, state-of-the-art baselines regarding both the two objectives (i.e., rumor influence strength and transmission time).

Rumor suppression is targeted at diminishing the impact of false and negative information within social networks by decreasing the prevalence of belief in such rumors among individuals, utilizing diverse strategies. Previous studies have broadly delineated rumor suppression strategies into two primary categories: targeting key nodes or edges for obstruction, and enlisting high-influence nodes to disseminate truth-related accurate information. Traditionally, employing a singular strategy involves utilizing a static algorithm throughout the rumor suppression endeavor. This method, however, encounters difficulties in adapting to fluctuating external conditions, rendering it less efficacious in the management of rumor proliferation. In response to these challenges, we introduce the concept of Adaptive Rumor Suppression (ARS), which aims to dynamically counter rumors by taking into account the nuances of propagation dynamics and the surrounding environmental context. We propose a multi-label state transition linear threshold model to more closely mirror the complex process of information diffusion across social networks. Furthermore, we advocate for a multi-round hybrid strategy that amalgamates blocking and clarification tactics to address the ARS problem within the confines of limited resource allocations. To navigate the complexities of ARS, we introduce the Hybrid Strategy of Each Round (HS-R) algorithm, which synergizes multiple strategies to effectively counter the spread of rumors. In extension, we present the Multi-Round Multi-Label (MRML) algorithm, designed to augment the efficiency of the HS-R algorithm. Experimental evaluations conducted on authentic social network datasets illustrate that our methodologies significantly outshine baseline algorithms, offering a more effective and adaptable solution to curb rumor propagation across varied environments.