Interpretable Learning for Detection of Cognitive Distortions from Natural Language Text

ACL ARR 2025 May Submission388 Authors

Abstract: We developed a technology that, based on a dataset annotated for cognitive distortions, builds an interpretable model capable of detecting cognitive distortions in natural language texts. The learning and detection technologies are based on structural pattern (N-gram) matching with the ”priority on order” principle. We investigated and released two types of detection models: plain binary classification and a model based on a multi-class representation. We optimized the hyper-parameters of the models and achieved an accuracy of 0.92 and an F1 score of 0.95 in a cross-validation experiment. Additionally, we achieved over 1000 times higher performance and lower computational cost compared to LLM-based alternatives.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: healthcare applications, clinical NLP, NLP for social good, stance detection, feature attribution, topic modeling, model editing

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches to low-resource settings, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models

Languages Studied: English

Keywords: healthcare applications, clinical NLP, NLP for social good, stance detection, feature attribution, topic modeling, model editing

Submission Number: 388