nowUP: A System that Automatically Creates TV Summaries Based on Twitter Activity

Abstract

Users post a lot of related TV information on social networks while they are watching TV, mostly in a connected way with the highlight moments of the TV shows. This paper reports on the nowUP project, targeted at the development of a service that automatically creates summaries of TV programs based on the buzz on social networks. The project premise relies on the idea that social media buzz has the potential to be used as an automatic editorial criterion. In this framework, the project goals include the development of a solution that automatically produces TV summaries of popular television programs (like football matches, talent or reality shows) based on the Twitter activity. The solution is based on a data-mining engine that processes the activity of this social network looking for tweets related with TV shows. Based on the program metadata it indexes the twitter activity; correlates tweets; and creates clusters of peaks, being the relevant clusters associated with the TV highlights. With this, a specific developed video engine automatically edits and creates a full video summary (an edited sequence of TV highlights) and publishes it in an online platform. The paper reports on the solution architecture and features and on the results of its preliminary evaluation. The results show that the solution was very successful in achieving the project main goal and the users are willing to have access to this type of social buzz-based video summaries.