Neural Topic Modeling of Psychotherapy Sessions
This work addresses the problem of improving psychotherapy effectiveness for therapists by offering interpretable topic insights, but it is incremental as it applies existing methods to a new domain.
The paper compared neural topic modeling methods to analyze psychotherapy session transcripts, incorporating temporal modeling to track topic similarities over time at turn-level resolution, aiming to provide interpretable insights for therapists.
In this work, we compare different neural topic modeling methods in learning the topical propensities of different psychiatric conditions from the psychotherapy session transcripts parsed from speech recordings. We also incorporate temporal modeling to put this additional interpretability to action by parsing out topic similarities as a time series in a turn-level resolution. We believe this topic modeling framework can offer interpretable insights for the therapist to optimally decide his or her strategy and improve psychotherapy effectiveness.