What does this research mean for the field?

The Multi-Relational Temporal-Semantic Augmented Dynamic Graph Neural Network (MRTS), which utilizes adaptive temporal segmentation and a triple-view dynamic graph, outperforms existing state-of-the-art baselines in social media rumor detection. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

The study aims to improve online rumor detection by addressing the rigid snapshot intervals and limited relational modeling in existing dynamic graph neural networks.

August 23, 2026Complex & Intelligent SystemsOpen Access

Social media rumor detection using multi-relational temporal-semantic augmented dynamic graph neural networks

View Full Paper

Ask AI

Bookmark

Authors

ALAilin LiGansu Institute of Political Science and Law JWJizong WangGansu Institute of Political Science and Law ZWZhihang WangUniversity of Derby

Discussion

Member takes

Implication

Computational study demonstrates improved social media rumor detection via multi-relational dynamic graph neural networks, suggesting enhanced modeling of fast-moving online misinformation.

Key Points

The study aims to improve online rumor detection by addressing the rigid snapshot intervals and limited relational modeling in existing dynamic graph neural networks.
Developed the Multi-Relational Temporal-Semantic Augmented Dynamic Graph Neural Network (MRTS) featuring an adaptive temporal segmentation strategy based on propagation velocity.
Constructed a unified triple-view dynamic graph combining user interaction, propagation structure, and semantic similarity views.
Implemented a spatio-temporal feature learning module incorporating cross-modal synergistic attention and a relation-aware time-decay fusion unit, evaluated on two public real-world datasets.
MRTS outperformed existing state-of-the-art baseline models across standard benchmark evaluations on two public real-world datasets.
The adaptive segmentation and triple-view dynamic graph effectively reduced computational redundancy while capturing bursty information diffusion and implicit post relationships.

Cite This Study

Li et al. (2026) studied this question.

synapsesocial.com/papers/6a8aad417677a34114445763 https://doi.org/10.1007/s40747-026-02463-5

View Full Paper

Ask AI

Bookmark

Implication

Computational study demonstrates improved social media rumor detection via multi-relational dynamic graph neural networks, suggesting enhanced modeling of fast-moving online misinformation.

Social media rumor detection using multi-relational temporal-semantic augmented dynamic graph neural networks

Discussion

Member takes

Implication

Key Points

Cite This Study

Social media rumor detection using multi-relational temporal-semantic augmented dynamic graph neural networks

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider