Stress and Emotion Open Access Data: A Review on Datasets, Modalities, Methods, Challenges, and Future Research...

Area of Science:

• eHealth
• Wearable Technology
• Affective Computing

Background:

• Remote patient monitoring is crucial for personalized eHealth care.
• Emotion and stress recognition in eHealth faces challenges due to data subjectivity and complexity.

Purpose of the Study:

• To review open-access multimodal datasets for emotion and stress detection.
• To analyze dataset characteristics, acquisition methods, and classification challenges.

Main Methods:

• Focus on physiological signals from wearable devices.
• Review advanced data processing methods.
• Examine dataset features, acquisition, and classification.

Main Results:

• Notable advances in data collection and algorithm development exist.
• Limitations include real-world variability, individual differences, and objective validation difficulties.
• Self-reported and contextual data can improve performance but lack consistency.

Conclusions:

• Further research is needed to address privacy, long-term data annotation, and robustness in uncontrolled environments.
• Privacy-preserving strategies and interdisciplinary collaboration are essential for reliable, scalable emotion-aware eHealth systems.