User Emotion Recognition Based on Multi-class Sensors of Smartphone

In this paper, we study about the problem of how to recognize the user emotion based on smartphone data more really. With single data used in the previous studies, it cannot make a comprehensive response of user behavior patterns. So we collected fine-grained sensing data which could reflect user daily behavior fully from multiple dimensions based on smartphone, and then used multidimensional data feature fusion method and six classification methods such as Support Vector Machine (SVM) and Random Forests. Finally, we carried out contrast experiment with twelve volunteers´ hybrid data and personal data respectively to recognized user emotion based on discrete emotion model and circumplex emotion model. The results show that the multidimensional data feature fusion method we mentioned which could reflect user behavior comprehensively present high accuracy. The initial use of the hybrid data train only have 72.73% accuracy rate, but after personal data training the accuracy rate can reach 79.78%. In the experimental of different emotion model, circumplex emotion model is better than discrete emotion model.