Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.02172 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914242012119040 |
|---|---|
| author | Liu, Yijun Liu, Wu Gu, Xiaoyan Yao, Hantao Wang, Weiping Luo, Jiebo Zhang, Yongdong |
| author_facet | Liu, Yijun Liu, Wu Gu, Xiaoyan Yao, Hantao Wang, Weiping Luo, Jiebo Zhang, Yongdong |
| contents | Rumor propagation modeling is critical for understanding and mitigating misinformation. Existing approaches combining rule-based regular agents with LLM-driven core agents provide a promising paradigm for large-scale rumor simulation. However, overlooking the dynamic nature of core agents and the importance of network topology on rumor spread significantly undermines the simulation performance. To address these issues, we present RumorSphere, a dynamic and hierarchical resonance framework for effective rumor simulation at the million-agent scale. Considering the dynamic role of core agents in rumor evolution, we propose a multi-agent dynamic interaction strategy based on the information cocoon theory, which adaptively identifies and activates critical core agents at conflict boundaries using LLMs, effectively supporting simulations with millions of agents. In addition, we design a hierarchical resonance network that integrates opinion leaders and localized community structures, enabling more realistic modeling of explosive rumor spread in real-world scenarios. Experiments on real-world datasets show that RumorSphere outperforms state-of-the-art methods, reducing simulation bias by an average of 26.5%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02172 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RumorSphere: A Framework for Million-scale Agent-based Dynamic Simulation of Rumor Propagation Liu, Yijun Liu, Wu Gu, Xiaoyan Yao, Hantao Wang, Weiping Luo, Jiebo Zhang, Yongdong Social and Information Networks Rumor propagation modeling is critical for understanding and mitigating misinformation. Existing approaches combining rule-based regular agents with LLM-driven core agents provide a promising paradigm for large-scale rumor simulation. However, overlooking the dynamic nature of core agents and the importance of network topology on rumor spread significantly undermines the simulation performance. To address these issues, we present RumorSphere, a dynamic and hierarchical resonance framework for effective rumor simulation at the million-agent scale. Considering the dynamic role of core agents in rumor evolution, we propose a multi-agent dynamic interaction strategy based on the information cocoon theory, which adaptively identifies and activates critical core agents at conflict boundaries using LLMs, effectively supporting simulations with millions of agents. In addition, we design a hierarchical resonance network that integrates opinion leaders and localized community structures, enabling more realistic modeling of explosive rumor spread in real-world scenarios. Experiments on real-world datasets show that RumorSphere outperforms state-of-the-art methods, reducing simulation bias by an average of 26.5%. |
| title | RumorSphere: A Framework for Million-scale Agent-based Dynamic Simulation of Rumor Propagation |
| topic | Social and Information Networks |
| url | https://arxiv.org/abs/2509.02172 |