"Making you happy makes me happy" -- Measuring Individual Mood with Smartwatches
This work addresses mood prediction for individuals using wearable technology, but it is incremental as it applies existing methods to new sensor data.
The paper tackles the problem of measuring individual happiness by interpreting smartwatch sensor data, achieving up to 94% prediction accuracy using random forests and finding that weather data strongly influences mood.
We introduce a system to measure individual happiness based on interpreting body sensors on smartwatches. In our prototype system we use a Pebble smartwatch to track activity, heartrate, light level, and GPS coordinates, and extend it with external information such as weather data, humidity, and day of the week. Training our machine learning-based mood prediction system using random forests with data manually entered into the smartwatch, we achieve prediction accuracy of up to 94%. We find that besides body signals, the weather data exerts a strong influence on mood. In addition our system also allows us to identify friends who are indicators of our positive or negative mood.