Achieving Online and Scalable Information Integrity by Harnessing Social Spam Correlations

Abstract

Malicious web links, social rumors, fraudulent advertisements, faked comments, and biased propaganda are overwhelmingly influencing online social networks. Enabling information integrity is a hot topic in both academia and industry. Traditional social spam detection techniques rely on centralized processing, focusing only on one specific set of data sources, thereby ignoring the social spam correlations between distributed data sources. In this paper, we propose an online and scalable misinformation detection system, named Spiral, to uncover social spam by leveraging the correlations between different social data sources in geo-distributed sites. The key insight in our approach is to amplify the effectiveness of state-ofthe-art techniques to detect inappropriate posts by enabling the efficient large-scale propagation of detection information across domains. The novelty of our design lies in three key components: (1) a decentralized distributed hash-table-based tree overlay deployment for harvesting and uncovering deceptive information spreading in multiple online social networks communities; (2) a progressive aggregation tree for collecting the properties of these posts and creating new classifiers to actively filter out the propagation of inappropriate posts; and (3) a group communication structure that allows multiple groups to exchange the correlations among distributed social data sources. We designed and implemented a prototype of the Spiral system. Our large-scale experiments, using real-world social data, demonstrate Spiral's scalability, effective loadbalancing, and efficiency in online spam detection for social networks.

MSCMGTB: A Novel Approach for Multimodal Social Media Content Moderation Using Hybrid Graph Theory and Bio-Inspired Optimization

“…These studies highlight the growing complexity of social media content and the need for sophisticated analysis tools. Xu et al [7] addressed the challenge of achieving online and scalable information integrity by harnessing social spam correlations, emphasizing the need for scalable solutions in content moderation. Ma et al [8] and Fei et al [9] explored social graph neural network-based interactive recommendation schemes and real-time detection of events from Twitter, respectively, showcasing the application of neural networks in capturing complex social interactions.…”

“…This perspective provides a novel framework for understanding and mitigating the spread of fake news. Finally, Xu et al [50] focused on achieving online and scalable information integrity by harnessing social spam correlations. Their research highlights the importance of scalability and adaptability of moderation systems in the rapidly evolving social media landscape.…”

“…The primary concerns revolve around computational efficiency and the ability to scale effectively on various social media platforms. These challenges necessitate innovative solutions that not only enhance accuracy but also ensure practical deployments [5][6][7][8]. The introduction of a Bi-directional Attention Mechanism (BAM) for text-visual fusion further refines this model.…”