Trusted commonsense knowledge enhanced depression detection based on three-way decision

Jie Chen, Hui Yao, Shu Zhao, Yanping Zhang

Abstract: Highlights•We enhance social media posts with trusted commonsense knowledge to improve the accuracy of depression detection.•We employ clinical scales and three-way decision theory to screen out the parts from the vast number of user posts that are most in need of enhancement.•We utilize an adaptive framework to generate and select commonsense knowledge for the parts that most require enhancement, ensuring the trustworthiness of the knowledge.•We dynamically adjust weights using gating and attention mechanisms, allowing the model to focus on the most critical parts.•Through experiments, we demonstrate that the trustworthiness of knowledge significantly impacts the accuracy of depression detection.