An AI-Supported Methodology for Identifying Attachment Styles

Identifying attachment styles is important for clinical psychologists interested in better understanding their patients. Traditional methods for identifying attachment styles rely on clinical interviews or questionnaires, which are time-consuming and subject to observer bias. Large Language Models offer potential for automated, objective attachment style analysis. The aim of the paper was to develop and validate an AI-supported methodology for identifying attachment styles using the four-category model. To validate the methodology, we analyzed the narratives of a unique group of subjects who experienced an acute psychological crisis. A LLM was used to analyze each stage using a structured prompt. We hypothesized that if the methodology validly identifies attachment styles, the fearful style would be the most prevalent in the descriptions of the subjects insecure childhood and crises. The methodology successfully identified the theoretically predicted attachment styles. Chi-square analyses confirmed significant deviations from the null hypothesis across all stages with a strong effect size. In sum, the AI-supported attachment analysis offers an objective, efficient alternative to traditional methods while maintaining theoretical validity. The methodology demonstrates potential clinical utility for rapid assessment of attachment dynamics, though further validation across diverse populations is warranted.