WEARS: Wearable Emotion AI with Real-time Sensor data
This work addresses emotion recognition for users in daily life by leveraging wearable sensors, but it is incremental as it applies existing methods to a new modality with limited dataset size.
The paper tackled emotion prediction by developing a system using smartwatch sensors to classify moods as pleasant or unpleasant, achieving a maximum accuracy of 93.75% with a Multi-Layer Perceptron model.
Emotion prediction is the field of study to understand human emotions. Existing methods focus on modalities like text, audio, facial expressions, etc., which could be private to the user. Emotion can be derived from the subject's psychological data as well. Various approaches that employ combinations of physiological sensors for emotion recognition have been proposed. Yet, not all sensors are simple to use and handy for individuals in their daily lives. Thus, we propose a system to predict user emotion using smartwatch sensors. We design a framework to collect ground truth in real-time utilizing a mix of English and regional language-based videos to invoke emotions in participants and collect the data. Further, we modeled the problem as binary classification due to the limited dataset size and experimented with multiple machine-learning models. We also did an ablation study to understand the impact of features including Heart Rate, Accelerometer, and Gyroscope sensor data on mood. From the experimental results, Multi-Layer Perceptron has shown a maximum accuracy of 93.75 percent for pleasant-unpleasant (high/low valence classification) moods.