Creating a Clinical Psychology Dataset with Synthetic Data: Automatic Detection of Cognitive Distortions Classified with NLP
Year: 2025
Type: article
Abstract: Advancements in the fields of machine learning and natural language processing have brought about the automatic detection of cognitive distortion expressions. Cognitive distortions are thinking errors that cause individuals to perceive reality misleadingly and have a strong relationship with psychopathologies. Therefore, accurately identifying and classifying distortions can enhance the effectiveness of Cognitive Behavioral Therapy (CBT). The number of data is quite a crucial factor in natural language processing tasks. Certain factors presented by clinical psychology, like confidentiality, pose one of the biggest challenges for researchers in terms of data access. This study employs the GPT-4 model to generate a synthetic data set of cognitive distortions, which is then classified using the roBERTa model. The aim is to assess the impact of incorporating synthetic data into cognitive distortion datasets. The results show that GPT-4 effectively simulates cognitive distortions. Additionally, roBERTa classifies these distortions accurately, and the integration of synthetic data into existing datasets enhances performance. These findings suggest that natural language processing (NLP) technologies could be a potential tool for the automatic detection and classification of cognitive distortions. The use of synthetic data could be a significant breakthrough both in cognitive therapy applications and in general mental health research.
Language: English
Topic: Mental Health via Writing
Subfield: Social Psychology
Field: Psychology
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W4408763870