The Language of Attachment: Modeling Attachment Dynamics in Psychotherapy

2025-04-22

AI Summary

Attachment style assessment relies on time-intensive, manual PACS coding, hindering the scalable implementation of attachment-informed clinical practice and research. Method: This study introduces the first clinically oriented NLP classification framework for automatically identifying patients’ attachment styles from psychotherapy session transcripts. It integrates clinically grounded linguistic feature modeling and incorporates error-impact weighting to quantify the differential therapeutic consequences of distinct misclassification types. Contribution/Results: We demonstrate the feasibility of automated attachment classification—achieving significantly higher accuracy than baseline models. The framework establishes the first scalable, clinically sensitive computational foundation for personalized intervention design, mechanistic investigation, and large-scale attachment research. By bridging theoretical constructs with empirical, real-world clinical data, it advances the translation of attachment theory into evidence-based practice.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Application Domains: Humanities & Computational Social Science

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Security and Privacy: Large-scale security measurements
• Web Mining and Content Analysis: Normalization, clustering, classification, and summarization of Web text

Abstract

The delivery of mental healthcare through psychotherapy stands to benefit immensely from developments within Natural Language Processing (NLP), in particular through the automatic identification of patient specific qualities, such as attachment style. Currently, the assessment of attachment style is performed manually using the Patient Attachment Coding System (PACS; Talia et al., 2017), which is complex, resource-consuming and requires extensive training. To enable wide and scalable adoption of attachment informed treatment and research, we propose the first exploratory analysis into automatically assessing patient attachment style from psychotherapy transcripts using NLP classification models. We further analyze the results and discuss the implications of using automated tools for this purpose -- e.g., confusing `preoccupied' patients with `avoidant' likely has a more negative impact on therapy outcomes with respect to other mislabeling. Our work opens an avenue of research enabling more personalized psychotherapy and more targeted research into the mechanisms of psychotherapy through advancements in NLP.

Problem

• Automatically assess patient attachment style from therapy transcripts
• Replace manual PACS coding with NLP classification models
• Improve therapy personalization via NLP-based attachment analysis

Innovation

• Using NLP to assess patient attachment style
• Automating PACS with classification models
• Enabling personalized psychotherapy via NLP