Textual forma mentis networks bridge language structure, emotional content and psychopathology levels in adolescents

2025-05-09

AI Summary

This study addresses the challenge of predicting adolescent psychopathological dimensions—including social maladaptation, internalizing behaviors, and neurodevelopmental risk—using natural language. Method: We introduce the Textual Form Mind Network (TFMN), a cognition-informed computational framework that extracts linguistic structure, semantic associations, and affective features from emotion-themed interview transcripts. TFMN-derived network topological metrics (e.g., modularity, betweenness centrality, local efficiency) are modeled via random forest and XGBoost regression, with SHAP-based interpretability analysis to quantify associations with clinical outcomes. Contribution/Results: To our knowledge, this is the first application of a cognition-driven TFMN model for adolescent psychopathology prediction. It achieves robust cross-validated prediction across all three dimensions (r = 0.33–0.37, p < 0.05) and identifies disgust-related emotional expression as a biopsycholinguistic marker linked to core-periphery network architecture—providing interpretable, computational neurolinguistic evidence supporting natural language as an early phenotypic indicator of psychiatric risk.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Application Domains: Humanities & Computational Social Science

Application Category

• Social Networks and Social Media: Computational social science
• Web Mining and Content Analysis: Large pretrained models with web data
• User Modeling, Personalization and Recommendation: Psychology-informed user models and recommender systems

Abstract

We introduce a network-based AI framework for predicting dimensions of psychopathology in adolescents using natural language. We focused on data capturing psychometric scores of social maladjustment, internalizing behaviors, and neurodevelopmental risk, assessed in 232 adolescents from the Healthy Brain Network. This dataset included structured interviews in which adolescents discussed a common emotion-inducing topic. To model conceptual associations within these interviews, we applied textual forma mentis networks (TFMNs)-a cognitive/AI approach integrating syntactic, semantic, and emotional word-word associations in language. From TFMNs, we extracted network features (semantic/syntactic structure) and emotional profiles to serve as predictors of latent psychopathology factor scores. Using Random Forest and XGBoost regression models, we found significant associations between language-derived features and clinical scores: social maladjustment (r = 0.37, p<.01), specific internalizing behaviors (r = 0.33, p<.05), and neurodevelopmental risk (r = 0.34, p<.05). Explainable AI analysis using SHAP values revealed that higher modularity and a pronounced core-periphery network structure-reflecting clustered conceptual organization in language-predicted increased social maladjustment. Internalizing scores were positively associated with higher betweenness centrality and stronger expressions of disgust, suggesting a linguistic signature of rumination. In contrast, neurodevelopmental risk was inversely related to local efficiency in syntactic/semantic networks, indicating disrupted conceptual integration. These findings demonstrated the potential of cognitive network approaches to capture meaningful links between psychopathology and language use in adolescents.

Problem

• Predict adolescent psychopathology using language network features
• Link language structure and emotions to clinical symptom scores
• Analyze linguistic signatures of social and neurodevelopmental risks

Innovation

• Network-based AI framework predicts adolescent psychopathology
• Textual forma mentis networks model word associations
• Explainable AI reveals language-psychopathology links