PsyDI: Towards a Personalized and Progressively In-depth Chatbot for Psychological Measurements

TL;DR

PsyDI is a novel personalized chatbot that uses multi-modal data and multi-turn interactions to provide accurate psychological measurements, exemplified by MBTI, with validated efficacy and high user engagement.

Contribution

This paper introduces PsyDI, a personalized, progressively in-depth chatbot for psychological assessment that leverages a new training paradigm and multi-turn interactions for precise MBTI measurement.

Findings

Validated the effectiveness of the score model in psychological measurement

Achieved high user engagement with over 3,000 visits

Collected multi-turn dialogues annotated with MBTI types

Abstract

In the field of psychology, traditional assessment methods, such as standardized scales, are frequently critiqued for their static nature, lack of personalization, and reduced participant engagement, while comprehensive counseling evaluations are often inaccessible. The complexity of quantifying psychological traits further limits these methods. Despite advances with large language models (LLMs), many still depend on single-round Question-and-Answer interactions. To bridge this gap, we introduce PsyDI, a personalized and progressively in-depth chatbot designed for psychological measurements, exemplified by its application in the Myers-Briggs Type Indicator (MBTI) framework. PsyDI leverages user-related multi-modal information and engages in customized, multi-turn interactions to provide personalized, easily accessible measurements, while ensuring precise MBTI type determination. To address the challenge of unquantifiable psychological traits, we introduce a novel training paradigm that involves learning the ranking of proxy variables associated with these traits, culminating in a robust score model for MBTI measurements. The score model enables PsyDI to conduct comprehensive and precise measurements through multi-turn interactions within a unified estimation context. Through various experiments, we validate the efficacy of both the score model and the PsyDI pipeline, demonstrating its potential to serve as a general framework for psychological measurements. Furthermore, the online deployment of PsyDI has garnered substantial user engagement, with over 3,000 visits, resulting in the collection of numerous multi-turn dialogues annotated with MBTI types, which facilitates further research. The source code for the training and web service components is publicly available as a part of OpenDILab at: https://github.com/opendilab/PsyDI