基于兴趣变化的微博用户转发行为建模

Modeling of the forwarding behavior in microblogging with adaptive interest

社交媒体的出现推动了对用户在线行为规律的研究。该文探讨微博中用户的转发行为规律。对这一问题的回答能够帮助人们更好地理解影响用户行为的因素,并且对用户转发行为的准确描述有利于对信息传播施加干预和控制。该文参考一个兴趣驱动的人类行为动力学模型,在分析其用户行为时长的基础上,针对差异化的用户行为时长和昼夜作息因素,提出了一个改进模型用以描述微博用户的转发行为。实际数据中用户相邻转发行为时间间隔呈现重尾分布,仿真结果与之相符,证明了该模型的有效性和灵活性。

The emergence of social media has given rise to research on how online users behave. This paper describes how users forward messages in microblogging services. The results shed light on the factors affecting user decisions. A precise description of user forwarding behavior can also support the intervention and control of in- formation spreading. The lengths of activity periods in existing human dynamic models with adaptive interest were used to develop a modified model to describe user forwarding dynamics in microblogging services. This model takes into account both the differences in the durations of the activity cycles and the effect of circadian rhythms. The distribution of the time intervals between successive forwarding activities is heavy-tailed in the real data. The simulation results are consistent with the distribution in the real data which demonstrates the effectiveness and flexibility of this model.