Mental disturbance impacting wellness dimensions: Resources and open research directions

In light of the unparalleled pressure faced by the healthcare system, there arises a pressing need for innovative solutions to comprehensively assess the overall well-being of individuals affected by mental health issues. With the objective of advancing AI-driven mental health analysis towards fine-grained analysis, we develop and publicly release our datasets, MULTIWD and WELLXPLAIN, specifically designed to capture the impact of mental disturbances on wellness dimensions in self-narrated texts. To this end, we make two major contributions. First, our examination focuses on the identification of one or more of the six distinct wellness dimensions evident within a given text, shedding light on the significant ramifications of mental disturbance, which, in turn, can perpetuate further mental unrest. Second, we conducting an extensive analysis of the textual cues that signify the presence of various wellness dimensions. We delve into the content of the text, examining specific linguistic and contextual markers that provide indications of the wellness dimensions being discussed. Finally, we open up future research directions to facilitate advancements in the domain of AI-driven approaches for fine-grained mental health analysis. This framework aims to establish and validate new clinical categories for mental distress, bridging the gap between mental wellness and illness, in response to the higher prevalence of distress compared to illnesses.