Leveraging Ecg Signals And Social Media For Stress Detection

Stress has become an important health issue with the rapid development of economy and society. The previous work has highlighted the discriminatory power of Electrocardiogram (ECG) and social media for stress detection. However, limitations exist when using single source data for stress detection. Based on the assumption that abnormal heart rate periods are usually caused by stressor or uplifting events, we present a way to integrate heart beat rates and linguistic posts on microblogs for stress detection. We first identify one's abnormal heart rate periods, and then for each such period, we pair up a temporally synchronous and highly matched abnormal posting (stressful/exciting) period detected from microblogs. Our 4-month user study with 10 volunteer college students shows that the performance of the matching between post-based detection results with ECG-based ones can achieve over 84% accuracy for stressful or exciting periods detection, and around 70% accuracy for stressor or uplifting events detection. The results also demonstrate that SDNN is the most appropriate indicators of ECG signals for daily abnormal heart rate and stress detection.