Research Area:  Machine Learning

Abstract:

Predicting the forthcoming stress is critical for stress management. In this article, we consider not only ones posts on social media, but also learn to understand the influence of stressor/uplift events and individuals reactions to the events by constructing an event-post correlation memory network, which evolves dynamically along with the change of events impact and ones response reflected from their posts. We further build a joint memory network for modeling the dynamics of ones emotions incurred by stressor/uplift events, and learn ones personality traits based on linguistic words and a fuzzy neural network. We finally predict ones future stress level based on a fully-connected network with attention, where personality traits, social activeness features, and forthcoming possible events are incorporated. We construct a dataset consisting of 1138 strongly-stressed and 985 weakly-stressed users on microblog. Experimental results show that: (1) our method outperformed the baseline, delivering 81.03 percent of prediction accuracy; (2) integrating the personality traits helped increase the prediction accuracy by 3.97 percent; (3) considering forthcoming events enabled to improve the prediction accuracy by 5.81 percent; (4) strongly-stressed users tended to be more neurotic and less active on social media, complying with psychological studies; (5) data scarcity had negative influence on stress prediction and (6) the dataset that is biased towards female made the model have a better prediction accuracy on female users.

Keywords:  
Stress
Social networking (online)
Predictive models
Correlation
Sensors
Linguistics
Data models

Author(s) Name:  Ningyun Li; Huijun Zhang; Ling Feng

Publisher name:  IEEE

DOI:  10.1109/TAFFC.2021.3076294

Volume Information:   Volume: 14

Paper Link:   https://ieeexplore.ieee.org/abstract/document/9417627