Robust suicide risk assessment on social media via deep adversarial learning

The prevalence of social media for sharing personal thoughts makes it a viable platform for the assessment of suicide risk. However, deep learning models are not able to capture the diverse nature of linguistic choices and temporal patterns that can be exhibited by a suicidal user on social media and end up overfitting on specific cues that are not generally applicable. We propose Adversarial Suicide assessment Hierarchical Attention (ASHA), a hierarchical attention model that employs adversarial learning for improving the generalization ability of the model.

We assess the suicide risk of a social media user across 5 levels of increasing severity of risk. ASHA leverages a transformer-based architecture to learn the semantic nature of social media posts and a temporal attention-based long short-term memory architecture for the sequential modeling of a user's historical posts. We dynamically generate adversarial examples by adding perturbations to actual examples that can simulate the stochasticity in historical posts, thereby making the model robust.

Through extensive experiments, we establish the face-value of ASHA and show that it significantly outperforms existing baselines, with the F1 score of 64%. This is a 2% and a 4% increase over the ContextBERT and ContextCNN baselines, respectively. Finally, we discuss the practical applicability and ethical aspects of our work pertaining to ASHA, as a human-in-the-loop framework.

Adversarial samples can be helpful in capturing the diverse nature of suicidal ideation. Through ASHA, we hope to form a component in a larger human-in-the-loop infrastructure for suicide risk assessment on social media.