Reproduce “Therapy-FIS: A Dataset for Assessing Facilitative Interpersonal Skills in Psychotherapeutic Setting” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Qijian Zheng, Wanqing Lin, Yuanfang Wang, Yijun Ge, Jordan Bate, Katie Aafjes-van Doorn, Feng Liu
DyadicFIS evaluates therapist interpersonal-skill ratings using public, standardized role-play data from 890 responses by 78 professionals. It uses derived facial, acoustic, and text features to predict observer ratings from therapist signals alone or with mock-patient context. In therapist-disjoint five-fold evaluation, it has the highest macro CCC in both tasks, though MDF has lower MSE in the joint-input task; the findings are not clinical validation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.