The rapid spread of rumors in social media is mainly caused by individual retweets. This paper applies uncertainty time series analysis (UTSA) to analyze a rumor retweeting behavior on Weibo. First, the rumor forwarding is modeled using uncertain time series, including order selection, parameter estimation, residual analysis, uncertainty hypothesis testing and forecast, and the validity of using uncertain time series analysis is further supported by analyzing the characteristics of the residual plot. The experimental results show that the uncertain time series can better predict the next stage of rumor forwarding. The results of the study have important practical significance for rumor management and the management of social media information dissemination.

翻译：社交媒体中谣言的快速传播主要由个体转发行为导致。本文应用不确定时间序列分析（UTSA）对微博上的谣言转发行为进行研究。首先，利用不确定时间序列对谣言转发进行建模，包括定阶、参数估计、残差分析、不确定假设检验与预测，并通过分析残差图的特征进一步支持了使用不确定时间序列分析的有效性。实验结果表明，不确定时间序列能够较好地预测谣言下一阶段的转发量。研究结果对谣言管控及社交媒体信息传播管理具有重要的实践意义。