Visual analytics methods for the automatic content generation from streaming data

We present a PhD project regarding the application of Visual Analytics (VA) methods for the automatic generation of wiki documents - i.e. wikification - and event storylines from streaming data. In contrast to static automatically generated wiki-like documents, this project investigates the employment of VA techniques for the automatic generation of wiki documents made up of dynamic contents, based on user preferences. The purpose of the project is to make the user an active component for the wikification process, able to provide useful feedback regarding which contents are more relevant for the topic of interest, thus improving the wikification algorithms. For this purpose, the project focuses on exploiting VA methods and data provenance to enhance data comprehension, by means of continuous interaction with the user according to the human-in-the-loop model.