Abstract
Depression is an important mental disease of global concern. Its complicated etiology and chronic clinical features make it difficult for users to be conscious of their own depression emotion and seriously threaten the patient's life safety. With the development of e-commerce, intelligent recommender system has brought new opportunities to personalized health monitoring for the users with emotional distress. Therefore, this paper puts forward the emHealth system, which is an intelligent health recommendation system with depression prediction for emotion health. This paper explores the monitoring and improvement of users psychological and physiological conditions by pushing personalized therapy solutions to patients with emotional distress. Specifically, this paper first proposes the system architecture of emHealth. Then, we design personalized mobile phone Apps to collect emotional data of users with tendentious depressive mood, and find the five main external characteristics of depression by Pearson correlation analysis. We divide 1047 volunteers data into training set and test set, and construct prediction model of depression using decision tree and support vector machine algorithms. For the different external factors that lead to depression, we give personalized recommendation and intelligent decision-making solution, and push related emotional improvement suggestions to guide users behavior. Finally, a specific application scene is demonstrated where patient's family member carry out psychological counseling for the patient, to verify the practicability and validity of the system. The beneficial effects of this system can meet the needs of the electronic market and can be promoted and popularized.