An End-to-End Set Transformer for User-Level Classification of Depression and Gambling Disorder
This work addresses early detection of mental health issues from social media data, offering an incremental improvement over existing methods by reducing label noise and enhancing interpretability.
The paper tackled user-level classification of depression and gambling disorder by processing sets of social media posts with a transformer architecture, achieving the best ERDE5 score of 0.015 for gambling detection and competitive scores for depression detection.
This work proposes a transformer architecture for user-level classification of gambling addiction and depression that is trainable end-to-end. As opposed to other methods that operate at the post level, we process a set of social media posts from a particular individual, to make use of the interactions between posts and eliminate label noise at the post level. We exploit the fact that, by not injecting positional encodings, multi-head attention is permutation invariant and we process randomly sampled sets of texts from a user after being encoded with a modern pretrained sentence encoder (RoBERTa / MiniLM). Moreover, our architecture is interpretable with modern feature attribution methods and allows for automatic dataset creation by identifying discriminating posts in a user's text-set. We perform ablation studies on hyper-parameters and evaluate our method for the eRisk 2022 Lab on early detection of signs of pathological gambling and early risk detection of depression. The method proposed by our team BLUE obtained the best ERDE5 score of 0.015, and the second-best ERDE50 score of 0.009 for pathological gambling detection. For the early detection of depression, we obtained the second-best ERDE50 of 0.027.