计算机工程与应用2025，Vol.61Issue(6)：183-191,9.DOI:10.3778/j.issn.1002-8331.2310-0333
基于时间步局部动态交互的多任务谣言检测方法
Multi-Task Rumor Detection Method Based on Time-Step Dynamic Interaction
摘要
Abstract
Rumour detection aims to identify information on social media that has not been officially verified or artificially created.Today's social networks contain a pattern of dynamic relationships that are difficult to find,changing over time and dynamic interactions between different posts.This paper proposes a multi-task rumour detection method based on time step local dynamic interaction,which can capture the hidden dynamic correlation information in rumour spreading events.An efficient multi-task interaction method is designed,in which time step is used as the basic sharing unit,the local features learned are shared,and the sharing efficiency is greatly improved,so that the detection framework of local dynamic interaction and whole multi-task sharing is formed.Finally,the attention mechanism is used to filter the infor-mation that is more favorable for rumour detection in different tasks and different structural characteristics to improve the detection effect.Experiments on PHEME and WEIBO datasets show that this method has advanced performance.关键词
谣言检测/时间步局部动态交互/传播结构特征/多任务共享Key words
rumor detection/time-step local dynamic interactions/propagation structure characterization/multitask sharing分类
信息技术与安全科学引用本文复制引用
杨广浩,万书振,董方敏,王梦园..基于时间步局部动态交互的多任务谣言检测方法[J].计算机工程与应用,2025,61(6):183-191,9.基金项目
国家自然科学基金新疆联合基金重点项目(U1703261,U61871258) （U1703261,U61871258）
三峡库区生态环境教育部工程研究中心开放基金项目(KF2023-11). （KF2023-11）
