Despite advancements in socially aware navigation, robots still often behave inappropriately in social environments. To ensure successful application, robots must detect the human perceived appropriateness of their navigation behaviors. This paper presents a novel dataset covering a complete range of perceived appropriateness and uniquely incorporates human emotion and attention to facilitate the detection of perceived appropriateness of robot social navigation in pathways (PARSNiP). It is created based on a series of human-robot interaction experiments with 30 participants and a mobile robot. Several typical machine learning models are utilized to evaluate the dataset and analyze the contributions of different features in detecting perceived appropriateness. The results indicate that incorporating emotional and attentional features can significantly improve the accuracy of perceived appropriateness detection. There was an increase from 63% to 68% using algorithm-predicted emotional and attentional features, and a further increase to 79% with the emotion and attention data reported by the participants. With the dataset, researchers could train machine learning models to enable robots to detect perceived appropriateness accurately, fostering adaptations that improve their responsiveness and accuracy in social interactions. The dataset is available for download at https://github.com/duibcuiegiosahxois/PARSNiP.git, and videos will be shared upon request by contacting Y.Zhou-13@tudelft.nl.

Good sleep is conducive to the recovery process of hospital patients - and yet, in many wards, sleep duration and quality can often be suboptimal, in part due to modifiable hospital-related sounds and noises. At the neurological ward of the Reinier de Graaf hospital in Delft, the Netherlands, we developed and evaluated a prototype information exchange system to raise awareness of specific sounds as disturbing patients' sleep. The system both classifies different relevant sound events and tracks sleep quality (using a Fitbit device). This information is then visualized for patients and staff to present the influence of the soundscape on patients' sleep hygiene in a friendly and comprehensive way. We discuss the design process, including a context study and various evaluations of the technology, interface, and created affordances. Our initial findings indicate that visualizing hospital soundscapes may, indeed, support both patients and staff in their efforts towards better sleep hygiene.

Our interactions form an intricate 'dance' - a dance requiring a fluent integration of both expressivity (e.g. to approach someone) and sensitivity (e.g. detect if you 'should' approach someone). Work on behaving artefacts has focused mostly on the social, emotional and aesthetic qualities that can be evoked - expressed - through interactions involving such artefacts. Meanwhile, novel methods from social signal processing and affective computing are beginning to imbue artefacts with a reflective awareness - a sensitivity - to the emergent social aspects of the interaction. Can we empower the expressivity of behaving artefacts by integrating it with such sensitivity? With this workshop we aim to bring together a range of perspectives, on the performative and technological opportunities for such artefacts, as well as on their potential (adverse) social and societal implications; to jointly establish what will be necessary to achieve Expressive\Sensitive artefacts that positively enrich and participate in the 'dance' of social interaction.

The Internet of Things makes human activity data - what people do, how they move, how they socialise - an abundant resource. However, this rich and intimate perspective on people, which uniquely shape and characterise their behaviours, can have tremendous ethical implication if data is handled irresponsibly. Being personal, contextual and accessible, mobile devices are key facilitators of (ir)responsible collection and use of data. In this workshop, we will use the Future Workshop approach to develop a research agenda towards ethical data-centric design of intelligent behaviours. As part of this approach, we will (1) criticise the current mechanisms and infrastructure to frame ethical challenges, (2) fantasise on futures which support user and designer values, and (3) implement a research agenda for the MobileHCI community to emphasise the barriers to tackle. The outcomes of this workshop will foster ethical research and inspire the MobileHCI community.