As interactive technologies shape indoor environments, dominant design approaches prioritise optimisation, efficiency, and instrumental forms of socialisation. In contrast, architectural traditions of biophilic design show how interaction with nature supports emotions, attentional restoration, and physical health. Yet these insights are often overlooked in interactive indoor environments. In this paper, we advance biophilic design as an interaction design lens for technologically mediated indoor environments. Drawing on design sessions with architects, we examine how qualities of natural phenomena, beyond visual greenery, are translated into biophilic interaction indoors. We contribute a biophilic interaction design framework for indoor environments structured through: (1) seven biophilic dimensions that characterise the design space; (2) seven design values that articulate the experiential priorities shaping this space; and (3) six interaction forms that illustrate novel ways occupants interact with indoor environments. Our framework positions biophilic interaction as a multisensory process shaped through relations between people, technologies, and built environments.

Smart building design has predominantly focused on interactive experiences that enhance human comfort across measurable dimensions, namely thermal, respiratory, visual, and acoustic comfort. In contrast, architectural practices attend to inhabitation as subjective, situated, lived, and socially embedded experiences. This creates a gap between what can be sensed and regulated and the complexity of human experiences in buildings. We argue that an Affective Interaction (AfI) lens offers a way to bridge this gap, and deepen the role of interaction design research in architecture. We illustrate this through two exploratory studies using open-ended, in-situ methods that foreground lived experience and social interpretation. The AfI perspective revealed five Ways in which occupants interpret smart environments — from reading bodily cues and forecasting disruption to making sense of building automation. From these, we distil six Affective Practices and six Interaction Qualities that guide the future of interaction design research in buildings.

Advances in interaction design, architecture, and artificial intelligence offer new possibilities for built environments. Yet, most systems focus on improving physical parameters such as indoor air quality. While these enhance physical comfort, they often overlook an innate aspect of human experience - our connection with nature - fundamental to physical and mental health. In contrast, architecture offers a rich legacy of biophilic design that creates sensory-rich spaces evoking a connection to nature. What insights can biophilic architecture offer to guide interactive experiences in future buildings? Drawing on 13 expert interviews, we expose the gap between current biophilic practices in smart buildings and the multidimensional potential of nature-inspired design. We present eight themes reflecting expert imaginaries of biophilic futures and five design opportunities illustrating how emerging technologies can position biophilic interaction as multi-sensory, interpretive, and aligned with more-than-human, justice-oriented futures.

Built environments increasingly incorporate new forms of intelligence, creating opportunities for enhancing human interactive experiences with and within building spaces.This scoping review examines design interventions and discourses within the domain of "Smart Buildings".The goal is to identify and characterise the type of human experiences that research in this domain aims to address.Using a hybrid deductive-inductive coding approach, we analysed 192 papers related to human experiences and smart buildings from ACM Digital Library and Scopus published between 1996 and 2024.Our analysis revealed 11 distinct "targeted human experiences", 20 commonly used "design mechanisms" to achieve those design goals, as well as two typologies of "technological interventions".Our findings create a foundation for understanding building design research and the range of human experience they entail.

Emotion Recognition is a critical research area for enhancing human-computer interaction. Keystroke dynamics, a behavioral biometric capturing typing patterns, offers a non-intrusive, user-friendly method for recognizing emotions. We propose a Dual-Stream Transformer-based Emotion Recognition (DSTER) model, which leverages keystroke dynamics to determine emotional states. The DSTER model features a dual-stream architecture that separately extracts temporal-over-channel and channel-over-temporal information. Each stream employs multi-head self-attention mechanisms, Long-Short Term Memory (LSTM), and Convolutional Neural Network (CNN) layers, along with dense vector embeddings of keycode data, to improve the extraction of temporal and contextual information from typing sequences. To the best of our knowledge, the DSTER model is the first to integrate transformer architecture with keystroke dynamics for emotion recognition. Our experiments on a widely-used fixed-text dataset demonstrate that the DSTER model significantly outperforms the three most recent baseline models, achieving average F1 scores up to 0.989 and an average accuracy increase of up to 66.04%. Unlike the significant performance variations reported in baseline models, the DSTER model maintains consistent and robust performance across all five tested emotional states. Further analysis shows that the model performs better with longer window lengths and greater overlaps.

Eliciting and capturing drivers’ affective responses in a realistic outdoor setting with pedestrians poses a challenge when designing in-vehicle, empathic interfaces. To address this, we designed a controlled, outdoor car driving circuit where drivers (N=27) drove and encountered pedestrian confederates who performed non-verbal positive or non-positive road crossing actions towards them. Our findings reveal that drivers reported higher valence upon observing positive, non-verbal crossing actions, and higher arousal upon observing non-positive crossing actions. Drivers’ heart signals (BVP, IBI and BPM), skin conductance and facial expressions (brow lowering, eyelid tightening, nose wrinkling, and lip stretching) all varied significantly when observing positive and non-positive actions. Our car driving study, by drawing on realistic driving conditions, further contributes to the development of in-vehicle empathic interfaces that leverage behavioural and physiological sensing. Through automatic inference of driver affect resulting from pedestrian actions, our work can enable novel empathic interfaces for supporting driver emotion self-regulation.

Capturing drivers’ affective responses given driving context and driver-pedestrian interactions remains a challenge for designing in-vehicle, empathic interfaces. To address this, we conducted two lab-based studies using camera and physiological sensors. Our first study collected participants’ (N = 21) emotion self-reports and physiological signals (including facial temperatures) toward non-verbal, pedestrian crossing videos from the Joint Attention for Autonomous Driving dataset. Our second study increased realism by employing a hybrid driving simulator setup to capture participants’ affective responses (N = 24) toward enacted, non-verbal pedestrian crossing actions. Key findings showed: (a) non-positive actions in videos elicited higher arousal ratings, whereas different in-video pedestrian crossing actions significantly influenced participants’ physiological signals. (b) Non-verbal pedestrian interactions in the hybrid simulator setup significantly influenced participants’ facial expressions, but not their physiological signals. We contribute to the development of in-vehicle empathic interfaces that draw on behavioral and physiological sensing to in-situ infer driver affective responses during non-verbal pedestrian interactions.

We present ACE, the Art, Color and Emotion browser. ACE is a data driven web based platform for exploring the visual sentiment and emotion in artistic paintings over time. To that end, we train our own visual artistic sentiment extraction model by leveraging the artworks from the OmniArt dataset. With our model we are able to estimate the overall sentiment dominating in groups of artworks belonging to a specific time interval. To make the results interactive and explorable we designed an intuitive interface with a carefully considered shape, color and element placement enforcing a top-down interaction scheme. Moreover, we perform extensive control on resource utilisation to provide the smoothest possible user experience and quality of service while using ACE.