数据采集与处理2026，Vol.41Issue(3)：854-868,15.DOI:10.16337/j.1004-9037.2026.03.017
一种融合动态语义与图结构的对比学习谣言检测方法
Contrastive Learning Approach for Rumor Detection via Fusion of Dynamic Semantics and Graph Structure
摘要
Abstract
The rapid growth of social media has enabled rumors to spread swiftly through extensive online interactions,thereby significantly undermining public trust and destabilizing social order.However,existing rumor detection methods face notable limitations in modeling the dynamic semantic evolution of text and accurately capturing complex propagation patterns,and they often struggle to distinguish between ambiguous rumor categories.To address these challenges,we propose DySGCL(Dynamic semantic and graph feature fusion for contrastive rumor detection),a novel contrastive learning framework that fuses dynamic semantic representations with graph-based structural features.Specifically,we employ a hierarchical Transformer to extract global semantic embeddings from users'past posts,while a temporal convolutional module improves sensitivity to fine-grained semantic shifts.For structural modeling,we first simulate adversarial perturbations via edge removal,then leverage a graph attention network(GAT)to highlight critical interaction pathways in the propagation network.Finally,an integrated contrastive objective combining self-supervised and supervised signals further enhances the model's discriminative power.Experiments on the Twitter15 and Twitter16 benchmarks show that DySGCL outperforms state-of-the-art baselines by 1.8%and 2.0%in accuracy,respectively,validating its effectiveness in dynamic and complex rumor detection scenarios.关键词
谣言检测/动态语义表示/图神经网络/对比学习/鲁棒性增强Key words
rumor detection/dynamic semantic representation/graph neural network/contrastive learning/robustness enhancement分类
信息技术与安全科学引用本文复制引用
徐培淇,刘盾,李天瑞..一种融合动态语义与图结构的对比学习谣言检测方法[J].数据采集与处理,2026,41(3):854-868,15.基金项目
国家自然科学基金(62276217,62402424) （62276217,62402424）
中央高校基本科研业务费项目(2682024KJ005,2682024ZTPY021). National Natural Science Foundation of China(Nos.62276217,62402424) （2682024KJ005,2682024ZTPY021）
Fundamental Research Funds for the Central Universities(Nos.2682024KJ005,2682024ZTPY021). （Nos.2682024KJ005,2682024ZTPY021）
