Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression
This work addresses the problem of early depression detection for mental health monitoring, offering an incremental advance by integrating clinical scales with neural models to enhance explainability and efficiency in streaming data scenarios.
The paper tackles early risk detection of depression from online posts by proposing a psychiatric scale guided screening method that captures risky posts aligned with clinical depression dimensions, achieving simultaneous improvements in efficacy and efficiency for early detection.
Depression is a prominent health challenge to the world, and early risk detection (ERD) of depression from online posts can be a promising technique for combating the threat. Early depression detection faces the challenge of efficiently tackling streaming data, balancing the tradeoff between timeliness, accuracy and explainability. To tackle these challenges, we propose a psychiatric scale guided risky post screening method that can capture risky posts related to the dimensions defined in clinical depression scales, and providing interpretable diagnostic basis. A Hierarchical Attentional Network equipped with BERT (HAN-BERT) is proposed to further advance explainable predictions. For ERD, we propose an online algorithm based on an evolving queue of risky posts that can significantly reduce the number of model inferences to boost efficiency. Experiments show that our method outperforms the competitive feature-based and neural models under conventional depression detection settings, and achieves simultaneous improvement in both efficacy and efficiency for ERD.