An Adaptive Decision-Making System for Behavior Analysis Among Young Adults

The global spread of the pandemic, secure isolation regulations, logistical limitations, and delays in reopening educational institutions such as colleges and universities have all had a severe psychological impact. Students, in particular, are regarded as a vulnerable population, experiencing higher levels of fear, stress, depression, and unhealthy eating compared to the general population. To reduce these psychological consequences, the study provides a multi-dimensional evaluation approach to bridge the gap between governments and health institutions in preventing and controlling biological hazards, such as mental illness among students. In the aftermath of the pandemic, this study presents a comprehensive evaluation approach designed to mitigate the psychological impact on students by connecting governments and health institutions in preventing and controlling biological hazards, particularly mental illness. To establish complex and vague data concerning the discussed communities, psychological details were obtained in the complex spherical fuzzy \( \mathscr {N}\) $\mathcal{N}$ -soft context. An enhanced group decision-making methodology was then established in two phases. Initially, weight analytics were defined using the Reyni entropy technique. In the subsequent phase, the Combined Compromise Solution (CoCoSo) approach was applied to examine the possibilities. Students attending schools and colleges experience significant psychological impacts. To evaluate these effects, an analytical study was conducted, suggesting that improved educational amenities are necessary to mitigate these psychological consequences. Furthermore, the study validates the significance of the proposed decision system through its analysis. A unique score function is suggested for analyzing the psychological consequences among adults because it effectively addresses the ambiguity in periodic data, resulting in accurate and consistent judgments within a two-dimensional framework. Experts thoroughly analyzed the data using the complex spherical fuzzy \( \mathscr {N}\) $\mathcal{N}$ -soft set-integrated CoCoSo method, and its limitations were also addressed.