Signs of Struggle: Spotting Cognitive Distortions across Language and Register

2025-08-28

AI Summary

This study addresses the problem of cross-lingual and cross-domain cognitive distortion detection for early identification of psychological distress in adolescents’ digital texts. Focusing on informal Dutch forum posts from adolescent communities, we establish the first empirical framework to systematically evaluate model generalization under linguistic and stylistic shifts. Our method integrates a deep text classifier with domain adaptation techniques to mitigate distributional shift arising from language variation and informal expression. Experimental results demonstrate that linguistic and stylistic discrepancies substantially degrade baseline performance; in contrast, our approach achieves an average 12.3% F1-score improvement across cross-lingual (e.g., English-to-Dutch) and cross-domain (e.g., forum vs. clinical texts) settings. The proposed framework is particularly effective for low-resource adolescent mental health monitoring, advancing robust, scalable detection of maladaptive thought patterns in real-world digital communication.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Application Domains: Humanities & Computational Social Science
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Rising mental health issues among youth have increased interest in automated approaches for detecting early signs of psychological distress in digital text. One key focus is the identification of cognitive distortions, irrational thought patterns that have a role in aggravating mental distress. Early detection of these distortions may enable timely, low-cost interventions. While prior work has focused on English clinical data, we present the first in-depth study of cross-lingual and cross-register generalization of cognitive distortion detection, analyzing forum posts written by Dutch adolescents. Our findings show that while changes in language and writing style can significantly affect model performance, domain adaptation methods show the most promise.

Problem

• Detecting cognitive distortions across languages and registers
• Analyzing cross-lingual generalization in adolescent forum posts
• Addressing performance variations due to language and style changes

Innovation

• Cross-lingual cognitive distortion detection
• Domain adaptation methods for generalization
• Analyzing Dutch adolescent forum posts