Entropy-rate as prediction method for newspapers and information diffusion

This paper aims to show how some popular topics on social networks can be used to predict online newspaper views, related to the topics. Newspapers site and many social networks, become a good source of data to analyse and explain complex phenomena. Understanding the entropy of a topic, could help all organizations that need to share information like government, institution, newspaper or company, to expect an higher activity over their channels, and in some cases predict what the receiver expect from the senders or what is wrong about the communication. For some organization such political party, leaders, company and many others, the reputation and the communication are (for most of them) the key part of a more and complex huge system. To reach our goal, we use gathering tools and information theory to detect and analyse trends topic on social networks, with the purpose of proved a method that helps organization, newspapers to predict how many articles or communication they will have to do on a topic, and how much flow of views they will have in a given period, starting with the entropy-article ratio. Our work address the issue to explore in which entropy-rate, and through which dynamics, a suitable information diffusion performance is expected on social network and then on newspaper. We have identified some cross-cutting dynamics that, associated with the contexts, might explain how people discuss about a topic, can move on to argue and informs on newspapers sites.