关键词: 情绪识别, 情绪模型, 机器学习, 智能手机

Abstract: This paper studies the problem how to recognize the user emotion based on smartphone data more really. With single data used in the previous research, it cannot make a comprehensive response of user behavior patterns. So this paper collects fine-grained sensing data which can reflect user daily behavior fully from multiple dimensions based on smartphone, and then uses multidimensional data feature fusion method and six classification methods such as support vector machine (SVM) and random forest. Finally, this paper carries out contrast experiments with twelve volunteers’ hybrid data and personal data respectively to recognize user emotion based on discrete emotion model and circumplex emotion model. The results show that the multidimensional data feature fusion method can reflect user behavior comprehensively and presents high accuracy. After personal data training, the accuracy rate of emotion recognition can reach 79.78%. In the experiments of different emotion models, the circumplex emotion model is better than discrete emotion model.

Key words: emotion recognition, emotion model, machine learning, smartphone