arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1609.09435cs.SIphysics.soc-phstat.AP
收藏

网络社交媒体中病毒式错误信息的统计特性

On the statistical properties of viral misinformation in online social media

Alessandro Bessi

摘要:

在线社交媒体的大规模传播使得阴谋论、恶作剧、未经证实的说法和虚假新闻迅速而不受控制地传播。如此大量的错误信息可能会影响政策偏好,并鼓励与建议做法截然不同的行为。在本文中,我们研究了在线社交媒体中病毒式错误信息的统计特性。通过属于极值理论的方法,我们表明,随着时间的推移,极端病毒帖子的数量遵循齐次泊松过程,并且这些帖子之间的到达时间是独立和同分布的,遵循指数分布。此外,我们还通过贝叶斯方法刻画了泊松过程速率参数的不确定性。最后,我们能够推导出在有限的时间间隔内超过一定阈值的帖子数量的预测后验概率分布。

英文摘要:

The massive diffusion of online social media allows for the rapid and uncontrolled spreading of conspiracy theories, hoaxes, unsubstantiated claims, and false news. Such an impressive amount of misinformation can influence policy preferences and encourage behaviors strongly divergent from recommended practices. In this paper, we study the statistical properties of viral misinformation in online social media. By means of methods belonging to Extreme Value Theory, we show that the number of extremely viral posts over time follows a homogeneous Poisson process, and that the interarrival times between such posts are independent and identically distributed, following an exponential distribution. Moreover, we characterize the uncertainty around the rate parameter of the Poisson process through Bayesian methods. Finally, we are able to derive the predictive posterior probability distribution of the number of posts exceeding a certain threshold of shares over a finite interval of time.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑