Leveraging natural language processing to enhance feedback-informed group therapy: A proof of concept.
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Group therapy has evolved as a powerful therapeutic approach, facilitating mutual support, interpersonal learning, and personal growth among members. However, the complexity of studying communication dynamics, emotional expressions, and group interactions between multiple members and often coleaders is a frequent barrier to advancing group therapy research and practice. Fortunately, advances in machine learning technologies, for example, natural language processing (NLP), make it possible to study these complex verbal and behavioral interactions within a small group. Additionally, these technologies may serve to provide leaders and members with important and actionable feedback about group therapy sessions, possibly enhancing the utility of feedback-informed care in group therapy. As such, this study sought to provide a proof of concept for applying NLP technologies to automatically assess alliance ratings from participant utterances in two community-based online support groups for weight stigma. We compared traditional machine learning approaches with advanced transformer-based language models, including variants pretrained on mental health and psychotherapy data. Results indicated that several models detected relationships between participant utterances and alliance, with the best performing model achieving an area under the receiver operating characteristic curve of 0.654. Logistic regression analysis identified specific utterances associated with high and low alliance ratings, providing interpretable insights into group dynamics. While acknowledging limitations such as small sample size and the specific context of weight stigma groups, this study provides insights into the potential of NLP in augmenting feedback-informed group therapy. Implications for real-time process monitoring and future directions for enhancing model performance in diverse group therapy settings are discussed. (PsycInfo Database Record (c) 2025 APA, all rights reserved).
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it