To recognize emotions using less obtrusive wearable sensors, we present a novel emotion recognition method that uses only pupil diameter (PD) and skin conductance (SC). Psychological studies show that these two signals are related to the attention level of humans exposed to visual stimuli. Based on this, we propose a feature extraction algorithm that extract correlation-based features for participants watching the same video clip. To boost performance given limited data, we implement a learning system without a deep architecture to classify arousal and valence. Our method outperforms not only state-of-art approaches, but also widely-used traditional and deep learning methods.

In September 2014, a local theatre company performed "the Tempest" simultaneously at two different locations to two separate audiences. Both audiences were linked together using an advanced video system, where several cameras captured the play. This is just one example of the radical shift in performing arts, where small theatre companies can use the Internet and a range of digital tools for reaching a wider remote audience. The question remains: what is the influence of this shift on the experience of the audience members? In order to better understand the problem space, we conducted two experiments focusing on two common current scenarios: remote asynchronous and synchronous watching of a theatre play. First, a theatre play was recorded and shown at a later date in a cinema to an audience. Second, a play in one theatre was broadcast to another theatre in real time. This paper reports the results of the experiments and discusses the implications towards the audience when bridging technology and performing arts. According to the results, a shift in time has a deep impact, with the audience rating their watching experience less intensive by 25% to the audience at the live venue. In the second experiment, on the other hand, both audiences reported fairly similar experiences, but different parts of the play had significant different impacts depending on the location where the audience was (in front of the stage or at another theatre). In particular it seems that lacking a way to show appreciation to the play e.g., applause has a big impact on the watching experience. The main conclusion though is that better mechanisms for including remote audiences in the experience are needed.

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.

Measuring the experience of audience of arts events is essential in the experience economy of this day and age, but it is a difficult task. The value of such information goes beyond evaluating the impact of the arts, as it can provide insights and feedback to enhance the work of artists and the experiences of other audience members. Through in-depth understanding of the needs of the providers and consumers of the arts, we progressively developed a biosensor infrastructure that was deployed in theaters. Over the years, we identified the challenges and issues related to developing and deploying a biosensor infrastructure in theaters. These collective experiences and identified issues were categorized into three main areas: processes, data, and system. A total of seven heuristics are developed across the three main areas. Processes place the stakeholders and audiences at the core of the research; data provides guidelines for data validity, collecting a variety of data, and supporting real-time data gathering; and systems covers the concurrency, scalability, deployment and feedback of the infrastructure. We believe that this set of heuristics forms the foundation for an adequate infrastructure to measure audience experience in the wild and it is a valuable source of guideline for future work.