Quadratic Diophantine fuzzy sentiment-based nonlinear decision-making for medical diagnostics through soft sets and cognitive maps

Decision-making is a complex process influenced by multiple factors, including available data, expert knowledge, contextual variables, stakeholder preferences, and emotional considerations. Despite the numerous methodologies proposed in recent years, there remains a need for more effective and intelligent techniques that address uncertainty in nonlinear, sentiment-based decision-making environments. In this paper, we develop and apply advanced nonlinear fuzzy models using quadratic Diophantine fuzzy soft sets and quadratic Diophantine fuzzy cognitive maps, with a particular focus on patient well-being through medical sentiment analysis. We begin with the quadratic Diophantine fuzzy soft set method to enhance the assessment of patient conditions through the analysis of symptoms, providing a precise evaluation of health status by considering multiple key factors. Next, the quadratic Diophantine fuzzy cognitive map method is used to identify the main elements influencing patient satisfaction by analyzing reviews on depression medications. This analysis also incorporates VADER-based sentiment analysis, implemented in Python, along with correlation analysis to quantify sentiment polarity in patient feedback on depression treatments. Collectively, these methods introduce nonlinear fuzzy tools that enhance evaluations and satisfaction assessments for effective sentiment-based decision-making. © 2025 The Authors