An AI-Supported Methodology for Identifying Attachment Styles

Abstract 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. Competing Interest Statement The authors have declared no competing interest. Funding Statement no funding Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: These subjects were selected in coordination with law enforcement authorities and the Witness Protection Authority, and the recruitment process received formal approval from the Ministry of National Security, which also supervised the interviews. Written and signed informed consent was obtained from each participant. Institutional Review Board (IRB) approval was obtained from the Government Office responsible for witness protection (ID: 08384917). The interview protocols were approved by the Bar-Illan University ethics committee (Date: 1.2.2018, No document ID). The second author, a Ph.D. student at Bar-Illan Univ., collected the data then. I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Footnotes email: kerenhazdai{at}gmail.com Data Availability Interviews are available upon request