Suicide is a leading cause of death around the world, interpolating a huge suffering to the families and communities of the individuals. Such pain and suffering are preventable with early screening and monitoring. However, current suicide risk identification relies on self-disclosure and/or the clinician's judgment.
Therefore, we investigate acoustic and nonverbal behavioral markers that are associated with different levels of suicide risks through a multimodal approach for suicide risk detection.Given the differences in the behavioral dynamics between subregions of facial expressions and body gestures in terms of timespans, we propose a novel region-based multimodal fusion.
We used a newly collected video interview dataset of young Japanese who are at risk of suicide to extract engineered features and deep representations from the speech, regions of the face (i.e., eyes, nose, mouth), regions of the body (i.e., shoulders, arms, legs), as well as the overall combined regions of face and body.
The results confirmed that behavioral dynamics differs between regions, where some regions benefit from a shorter timespans, while other regions benefit from longer ones. Therefore, a region-based multimodal approach is more informative in terms of behavioral markers and accounts for both subtle and strong behaviors. Our region-based multimodal results outperformed the single modality, reaching a sample-level accuracy of 96% compared with the highest single modality that reached sample-level accuracy of 80%. Interpretation of the behavioral markers, showed the higher the suicide risk levels, the lower the expressivity, movement and energy observed from the subject. Moreover, the high-risk suicide group express more disgust and contact avoidance, while the low-risk suicide group express self-soothing and anxiety behaviors.
Even though multimodal analysis is a powerful tool to enhance the model performance and its reliability, it is important to ensure through a careful selection that a strong behavioral modality (e.g., body movement) does not dominate another subtle modality (e.g., eye blink). Despite the small sample size, our unique dataset and the current results adds a new cultural dimension to the research on nonverbal markers of suicidal risks. Given a larger dataset, future work on this method can be useful in helping psychiatrists with the assessment of suicide risk and could have several applications to identify those at risk.