Having children as passengers in a car influences the parents' experience of driving. Concern for their safety often supersedes other considerations. When designing in-car solutions to address the special needs of children as passengers, one could aim for assisting the parents with this task. For such systems, it is important that the proposed solution is able to engage the children and keeps them from distracting the driver, while offering the children an interesting and meaningful way to spend their time in the car. We propose and evaluate a conceptual design that involves an interactive, full-speech companion that uses information from the drive to entertain and educate children. Our evaluation reveals that a robot companion is able to engage the children more than a similar system without a physical companion, giving them an entity to direct their interactions to. This finding makes it a worthwhile consideration for designers to add such components to their solutions.

Abstract. We present an approach that leverages on the knowledge present on the Web for identifying and enriching relevant items inside a News video and displaying them in a timely and user friendly fashion. This second screen prototype (i) collects and offers information about persons, locations, organizations and concepts occurring in the newscast, and (ii) combines them for enriching the underlying story along five main dimensions: expert's opinions, timeline, in depth, in other sources, and geo-localized comments from other viewers. Starting from preliminary insights coming from the named entities spotted on the subtitles, we expand this initial context to a broader event representation by relying in the knowledge of other Web documents talking about the same fact. An online demo of the proposed solution is available at http://www. linkedtv.project.cwi.nl/news/.

Abstract. TV newscasts report about the latest event-related facts occurring in the world. Relying exclusively on them is, however, insufficient to fully grasp the context of the story being reported. In this paper, we propose an approach that retrieves and analyzes related documents from the Web to automatically generate semantic annotations that provide viewers and experts comprehensive information about the news. We detect named entities in the retrieved documents that further disclose relevant concepts that were not explicitly mentioned in the original newscast. A ranking algorithm based on entity frequency, popularity peak analysis, and domain experts' rules sorts those annotations to generate what we call Semantic Snapshot of a Newscast (NSS). We benchmark this method against a gold standard generated by domain experts and assessed via a user survey over five BBC newscasts. Results of the experiments show the robustness of our approach holding an Average Normalized Discounted Cumulative Gain of 66.6%.

This article presents an end-to-end system for capturing physiological sensor data and visualising it on a real-time graphic dashboard and as part of an art installation. More specifically, it describes an event where the level of engagement of the audience was measured by means of Galvanic Skin Response (GSR) sensors and of the presenter through a sweater fitted with GSR, ECG and acceleration sensors. The gathered data was presented in real-time through a visualisation projected onto a screen and a physical electro-mechanical installation, which would change the height of helium-filled balloons depending on the atmosphere in the auditorium. Thereby trying to create a tangible way of making the invisible visible.

No abstract