Mining and modelling web user engagement: A survey on academic sites for framework establishment

The rapid development of information and communication technologies has made the Internet to become the main source of information, not to say a platform to share knowledge and information on a daily basis, consumed on various devices and platforms. This information consumption on the other hand produces data that can be used to measure user engagement into content and has been used for various purposes, e.g., for advertising and web personalization. The most common metric used has been click through rate. However, a simple click does not necessarily mean user engagement, although it can be one of the metrics applied. In this paper we focus on user engagement aspects and propose a framework to evaluate user engagement towards sites and provided web content. To demonstrate and prove the framework, we have conducted an extensive study on several websites in academic domain.