Introducing WARM-VR: Benchmark Dataset for Multimodal Wearable Affect Recognition in Virtual Reality

With the growing integration of human-computer interaction into everyday life, advances in machine learning have enabled systems to better perceive and respond to users’ emotional states. Affective computing, in particular, has emerged as a key area of research, leveraging continuous physiological signals from wearable sensors to detect and measure human affect. However, most existing affect recognition datasets focus on static environments, limiting their applicability to immersive multimedia contexts such as Virtual Reality (VR). In this paper, we introduce WARM-VR (Wearable Affect Recognition from Multisensory stimuli in Virtual Reality), a novel publicly available multimodal dataset designed to support affect recognition in immersive, multisensory environments using wearable sensing instrumentation. Data were collected from 28 participants aged 19–37 using wearable sensors: a wristband measuring Blood Volume Pulse (BVP), Electrodermal Activity (EDA), skin Temperature (TEMP), three-axis Acceleration (ACC), and a chest strap recording Electrocardiogram (ECG) signals. Participants engaged in immersive VR experiences designed to elicit relaxation through a calming beach environment following stress induction via an arithmetic task. These sessions incorporated synchronized multimedia stimuli: visual, auditory, and olfactory. Affective states were assessed subjectively through validated self-report questionnaires and objectively through the analysis of physiological measurements. Statistical analysis of the questionnaires confirmed that VR relaxation significantly reduced negative affect, particularly with olfactory enhancement. Furthermore, we established a benchmark on the dataset using widely recognized machine learning algorithms. The best performance for binary classification from BVP data of valence, was obtained with a CNN and a CNN–Bi-GRU model, both achieving an average F1-score of 0.63 and an AUC of 0.69. For arousal, a lightweight Transformer architecture provided the most balanced results (F1-0: 0.54 and F1-1: 0.63), outperforming recurrent hybrids. In the relaxation task, a CNN–Bi-GRU model reached the highest overall performance (average F1-score 0.64, AUC 0.69), with the Transformer variant achieving comparable accuracy. The WARM-VR dataset in this paper is made publicly available and can be downloaded from: DOI 10.21227/rwrm-n531