0


可以预测级联吗?

Can cascades be predicted?
课程网址: http://videolectures.net/solomon_leskovec_cascades_predicted/  
主讲教师: Jure Leskovec
开课单位: 斯坦福大学
开课时间: 2014-06-02
课程语种: 英语
中文简介:
社交网络在信息、想法、行为和产品的传播中起着核心作用。由于这种“传染病”在人与人之间传播,它们可能会“病毒性”传播,并形成大的级联效应。然而,越来越多的研究表明,病毒性和级联可能天生不可预测。因此,一个核心问题是信息级联是否可以预测,甚至可以设计。在本次演讲中,我将讨论一个预测级联并使其成为病毒的框架。我们研究了Facebook上的大量cascade样本,发现在预测cascade未来是否会继续增长方面有很强的表现。我们开发的模型帮助我们理解如何创建病毒式的社交媒体内容:在正确的时间为正确的社区使用正确的标题。
课程简介: Social networks play a central role in spreading of information, ideas, behaviors, and products. As such "contagions" diffuse from a person to person they may go “viral,” and large cascades can form. However, a growing body of research has argued that virality and cascades may be inherently unpredictable. Thus, one of the central questions is whether information cascades can be predicted and possibly even engineered. In this talk, I will discuss a framework for predicting cascades and making them go viral. We study large sample of cascades on Facebook and find strong performance in predicting whether a cascade will continue to grow in the future. The models we develop help us understand how to create viral social media content: by using the right title, for the right community, at the right time.
关 键 词: 社交网络; 级联效应; 信息级联
课程来源: 视频讲座网
数据采集: 2021-11-09:nkq
最后编审: 2021-11-09:nkq
阅读次数: 75