Process Knowledge-infused Learning for Suicidality Assessment on Social Media
This addresses the need for more interpretable AI in healthcare, specifically for suicidality assessment, though it appears incremental by building on existing explainable AI methods.
The paper tackles the problem of improving deep learning algorithms for suicidality assessment on social media by introducing Process Knowledge-infused Learning (PK-iL), which incorporates structured process knowledge to provide human-understandable explanations, resulting in a 0.72 annotator agreement for explanation quality and competitive performance with state-of-the-art baselines.
Improving the performance and natural language explanations of deep learning algorithms is a priority for adoption by humans in the real world. In several domains, such as healthcare, such technology has significant potential to reduce the burden on humans by providing quality assistance at scale. However, current methods rely on the traditional pipeline of predicting labels from data, thus completely ignoring the process and guidelines used to obtain the labels. Furthermore, post hoc explanations on the data to label prediction using explainable AI (XAI) models, while satisfactory to computer scientists, leave much to be desired to the end-users due to lacking explanations of the process in terms of human-understandable concepts. We \textit{introduce}, \textit{formalize}, and \textit{develop} a novel Artificial Intelligence (A) paradigm -- Process Knowledge-infused Learning (PK-iL). PK-iL utilizes a structured process knowledge that explicitly explains the underlying prediction process that makes sense to end-users. The qualitative human evaluation confirms through a annotator agreement of 0.72, that humans are understand explanations for the predictions. PK-iL also performs competitively with the state-of-the-art (SOTA) baselines.