Correlating Stressor Events for Social Network Based Adolescent Stress Prediction

The increasingly severe psychological stress damages our mental health in this highly competitive society, especially for immature teenagers who cannot settle stress well. It is of great significance to predict teenagers' psychological stress in advance and prepare targeting help in time. Due to the fact that stressor events are the source of stress and impact the stress progression, in this paper, we give a novel insight into the correlation between stressor events and stress series (stressor-stress correlation, denotes as SSC) and propose a SSC-based stress prediction model upon microblog platform. Considering both linguistic and temporal correlations between stressor series and stress series, we first quantify the stressor-stress correlation with KNN method. Afterward, a dynamic NARX recurrent neural network is constructed to integrate such impact of stressor events for teens' stress prediction in future episode. Experiment results on the real data set of 124 high school students verify that our prediction framework achieves promising performance and outperforms baseline methods. Integrating the correlation of stressor events is proved to be effective in stress prediction, significantly improving the average prediction accuracy.