The impact of alliance-focused and facilitative interpersonal relationship training on therapist skills: An RCT of brief training.

Research on standard methods of therapist training has found mixed evidence to as to whether standard training methods are effective. This study investigated the impact of a novel, research-informed training protocol that integrated elements of alliance-focused training (AFT) and facilitative interpersonal skills (FIS). Beyond traditional training techniques of didactics and lecture, the AFT/FIS intervention incorporated empirically supported video simulations of therapy, which were reinforced by role plays and deliberate practice on key therapeutic interpersonal skills. Fifty-eight graduate-level therapy trainees and professional therapists from various helping fields were randomized to one of two brief trainings in a multi-site RCT: (i) the AFT/FIS workshop or (ii) a more traditional demonstration training (DT) workshop. Participants were assessed on critical, relational therapeutic skills before and after the training. After controlling for relevant covariates, participants in the AFT/FIS training saw a marginally higher post-intervention level of overall therapeutic skills. Subsequent exploratory analyses revealed AFT/FIS participants also had significantly higher levels of specifically targeted post-training therapist skills (i.e., empathy, alliance bond capacity, and alliance rupture-repair responsiveness) compared to participants in DT. Implications for future empirical investigations and training initiatives are discussed.

Automatic rating of therapist facilitative interpersonal skills in text: A natural language processing application.

Background: While message-based therapy has been shown to be effective in treating a range of mood disorders, it is critical to ensure that providers are meeting a consistently high standard of care over this medium. One recently developed measure of messaging quality-The Facilitative Interpersonal Skills Task for Text (FIS-T)-provides estimates of therapists' demonstrated ability to convey psychotherapy's common factors (e.g., hopefulness, warmth, persuasiveness) over text. However, the FIS-T's scoring procedure relies on trained human coders to manually code responses, thereby rendering the FIS-T an unscalable quality control tool for large messaging therapy platforms. Objective: In the present study, researchers developed two algorithms to automatically score therapist performance on the FIS-T task. Methods: The FIS-T was administered to 978 messaging therapists, whose responses were then manually scored by a trained team of raters. Two machine learning algorithms were then trained on task-taker messages and coder scores: a support vector regressor (SVR) and a transformer-based neural network (DistilBERT). Results: The DistilBERT model had superior performance on the prediction task while providing a distribution of ratings that was more closely aligned with those of human raters, versus SVR. Specifically, the DistilBERT model was able to explain 58.8% of the variance (R 2 = 0.588) in human-derived ratings and realized a prediction mean absolute error of 0.134 on a 1-5 scale. Conclusions: Algorithms can be effectively used to ensure that digital providers meet a consistently high standard of interactions in the course of messaging therapy. Natural language processing can be applied to develop new quality assurance systems in message-based digital psychotherapy.