Artificial intelligence (AI) has advanced rapidly in natural language processing, yet it remains limited in interpreting the nuanced emotional and cognitive dimensions of human expression (Calvo et al., 2015; Picard, 1997). This limitation is particularly important in mental health, human-computer interaction, and social computing, where understanding subtle cognitive and emotional patterns is essential (Poria et al., 2017; Pennebaker et al., 2007). To address this, the study introduces a Cognitive-Emotive Mapping Framework, a structured method for analyzing human textual expression. It comprises four interconnected layers: emotional classification, cognitive pattern identification, intensity scaling, and risk signal detection, providing clear, reproducible insights into emotional states, cognitive tendencies, expression intensity, and indicators of psychological vulnerability (Le Glaz et al., 2021; Stewart MIT Media Lab, 2019). An example application demonstrates its practical utility in detecting cognitive distortions, emotional intensity, and potential psychological risk, offering actionable insights for research, education, and mental health interventions (Malgaroli et al., 2023; Khan, 2025). And so, by providing a reproducible, ethically grounded approach, this work contributes a human-centered methodology for integrating psychological insight into AI, bridging computational capability and human understanding.
Vynolyn Naidoo Vynolyn Naidoo (Sat,) studied this question.