Therapy-FIS: A Dataset for Assessing Facilitative Interpersonal Skills in Psychotherapeutic Setting
Organizations: College of Computer Science and Artificial Intelligence, Fudan University, Shanghai, P. R. China · Faculty of Arts and Sciences, New York University Shanghai, Shanghai, P. R. China · Global College, Shanghai Jiao Tong University, Shanghai, P. R. China · School of Psychology, Shanghai Jiao Tong University, Shanghai, P. R. China ·
Abstract
Facilitative Interpersonal Skills (FIS) is a performance-based assessment method that provides a structured framework for evaluating the interpersonal competencies of mental health professionals. However, existing FIS assessment relies heavily on human observer ratings, making the evaluation process labor-intensive, costly, and difficult to scale. Progress toward automated FIS assessment has also been constrained by the lack of publicly available professional data in psychotherapy settings. To address this limitation, we introduce Therapy-FIS, a dataset for automated FIS assessment in standardized psychotherapy tasks. To our knowledge, Therapy-FIS is the first publicly available dataset in this domain. It contains facial, acoustic, and textual signals derived from standardized therapist responses to standardized mock patient stimulus clips, based on 890 therapist video recordings and 8 patient videos, and is rated with eight FIS subscale ratings and an overall FIS score. Built on Therapy-FIS, we further establish a benchmark with two downstream tasks: Therapist Performance Rating and Joint Therapist--mock-Patient Performance Rating. We also introduce a competitive baseline, DyadicFIS, with gated fusion and routed readout under therapist-only and dyadic settings. DyadicFIS obtains the best macro CCC(Concordance Correlation Coefficient) scores on both tasks (0.2807 and 0.3299). Therapy-FIS offers a reproducible resource for data-driven automated assessment of therapeutic interpersonal skills in mental health.
Figures & tables
| Source | Counts | Mean (s) | Max (s) |
|---|---|---|---|
| Therapist | 890 | 67.29 | 278.19 |
| Patient | 8 | 96.82 | 123.66 |
| Task | Model | MSE | CCC |
|---|---|---|---|
| T1 | TimeSformer(2021) | 0.2027 0.0357 | 0.2125 0.0831 |
| DLinear(2023) | 0.2256 0.0283 | 0.0961 0.0408 | |
| Reformer(2020) | 0.2211 0.0352 | 0.1807 0.0400 | |
| MSGNet(2024) | 0.2184 0.0274 | 0.1759 0.0260 | |
| KANAD(2025) | 0.2096 0.0553 | 0.2043 0.0434 | |
| JMT(2024) | 0.2156 0.0416 | 0.1286 0.0316 |
| Category | Variant | CCC |
|---|---|---|
| Reference | Full | 0.3299 0.0556 |
| Module | w/o centroid residual | 0.3076 0.0689 |
| w/o dyadic interaction | 0.3234 0.0556 | |
| w/o modality gate | 0.3213 0.0907 | |
| Modality only | Audio only | 0.3241 0.0744 |
| Face only | 0.0105 0.0829 |
Automated Evaluation
Automated evaluation develops metrics, benchmarks, and AI judges to assess model outputs and system behavior at scale.
See all 422 papers