e-THERAPIST: I suggest you to cultivate a mindset of positivity and nurture uplifting thoughts
Submission Type: Regular Long Paper
Submission Track: Dialogue and Interactive Systems
Submission Track 2: Human-Centered NLP
Keywords: Dialogue Systems, Psychotherapy, Persona, Sentiment, Politeness, Interpersonal communication Strategy, Rewards, Reinforcement Learning
TL;DR: e-THERAPIST: a polite interpersonal psychotherapy dialogue system
Abstract: The shortage of therapists for mental health patients emphasizes the importance of globally accessible dialogue systems alleviating their issues. To have effective interpersonal psychotherapy, these systems must exhibit politeness and empathy when needed. However, these factors may vary as per the user's gender, age, persona, and sentiment. Hence, in order to establish trust and provide a personalized cordial experience, it is essential that generated responses should be tailored to individual profiles and attributes. Focusing on this objective, we propose e-THERAPIST, a novel polite interpersonal psychotherapy dialogue system to address issues like depression, anxiety, schizophrenia, etc. We begin by curating a unique conversational dataset for psychotherapy, called PsyCon. It is annotated at two levels: (i) dialogue-level - including user's profile information (gender, age, persona) and therapist's psychotherapeutic approach; and (ii) utterance-level - encompassing user's sentiment and therapist's politeness, and interpersonal behaviour. Then, we devise a novel reward model to adapt correct polite interpersonal behaviour and use it to train e-THERAPIST on PsyCon employing NLPO loss. Our extensive empirical analysis validates the effectiveness of each component of the proposed e-THERAPIST demonstrating its potential impact in psychotherapy settings.
Submission Number: 5279
Loading