Psychological Stress Detection from Social Media Data using a Novel Hybrid Model

Abstract

Psychological stress is considered as the biggest threat to individual’s health. Hence, it is vital to detect and manage stress before it turns into severe problem. However, conventional stress detection strategies rely on psychological scales and physiological devices, which require active individual participation making it labor-consuming, complex and expensive. With the rapid growth of social networks, people are willing to share moods via social media platforms making it practicable to leverage online social interaction data for stress detection. The developed novel hybrid model Psychological Stress Detection (PSD), automatically detect the individual’s psychological stress from social media. It comprises of three modules Probabilistic Naïve Bayes Classifier, Visual (Hue, Saturation, Value) and Social, to leverage text, image post and social interaction information we have defined the set of stress-related textual ‘F = {f1, f2, f3, f4}’, visual ‘vF = {vf1, vf2}’, social ‘sf’ to detect and predict stress from social media content. Experimental results show that the proposed PSD model improves the detection performance when compared to TensiStrength and Teenchat framework, PSD achieves 95% of Precision rate. PSD model would be useful in developing stress detection tools for mental health agencies and individuals.