Emotion Recognition for Everyday Life Using Physiological Signals From Wearables: A Systematic Literature Review

• Published in: IEEE transactions on affective computing Vol. 14; no. 3; pp. 1876 - 1897
• Main Authors: Saganowski, Stanislaw, Perz, Bartosz, Polak, Adam G., Kazienko, Przemyslaw
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.07.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: affective computing; Annotations; Bibliographies; Biomedical monitoring; Cognitive tasks; Data processing; Deep learning; Emotion recognition; Emotions; field studies; Literature reviews; Machine learning; Monitoring; personal device; Physiology; review; Self assessment; Self evaluation; Sensors; smart band; smartwatch; survey; systematic literature review; Systematics; validation; wearable; Wearable sensors
• ISSN: 1949-3045; 1949-3045
• DOI: 10.1109/TAFFC.2022.3176135

Smart wearables, equipped with sensors monitoring physiological parameters, are becoming an integral part of our life. In this work, we investigate the possibility of utilizing such wearables to recognize emotions in the wild. In most reviewed papers, the authors apply a similar procedure consisting of participant recruitment, stimuli preparation and annotation, signal collection and processing, self-assessment, and machine learning model learning and validation. Besides, we identified seven emotion recognition scenarios and analyzed the transition from psychological models to machine learning tasks. Even though the majority of the research was performed in the laboratory environment, we conclude that studies in the field are feasible. They require especially: (1) new self-assessment and triggering procedures adjusted to a real-life scenario, (2) more attention to the machine learning process, including suitable deep learning architectures, revision of the data imbalance problem, and subject-specific data processing, (3) adequate validation procedures, (4) consideration of the model generalizability versus personalizability, (5) comfortable devices able to provide reliable measurements in motion. Additionally, more large-scale studies are necessary to increase result credibility. We also postulate actions toward replicability and comparability of the research.