Computer Science

Exploring The Design of Prompts For Applying GPT-3 based Chatbots: A Mental Wellbeing Case Study on Mechanical Turk

H. Kumar, I. Musabirov, et al.

This innovative study explores the application of GPT-3 in crafting chatbots aimed at enhancing mood and mental well-being. Conducted by a team from the University of Toronto, it presents intriguing insights on prompt engineering, grounded in rigorous experimentation and user feedback.

00:00

Playback language: English

Index

Abstract

Large Language Models (LLMs) like GPT-3 offer the potential to create more human-like and helpful chatbots. This paper presents a case study evaluating the feasibility of a GPT-3-based chatbot designed for improving mood and mental well-being. A randomized factorial experiment with 945 Mechanical Turk participants tested three prompt design dimensions: identity, intent, and behavior. Quantitative and qualitative analyses of conversations and user perceptions are presented, offering insights into prompt engineering for GPT-3 chatbots and providing a methodology for HCI designers and researchers to build upon.

Publisher

ACM

Published On

Aug 22, 2022

Authors

Harsh Kumar, Ilya Musabirov, Jiakai Shi, Adele Lauzon, Kwan Kiu Choy, Ofek Gross, Dana Kulzhabayeva, Joseph Jay Williams

DOI

https://doi.org/10.48550/arXiv.2209.11344

Related Publications

Explore these studies to deepen your understanding of the subject.

Chemistry

A generative artificial intelligence framework based on a molecular diffusion model for the design of metal-organic frameworks for carbon capture

H. Park, X. Yan, et al.

Environmental Studies and Forestry

A new scheme for low-carbon recycling of urban and rural organic waste based on carbon footprint assessment: A case study in China

K. Zhou, Y. Li, et al.

Business

The government intervention effects on panic buying behavior based on online comment data mining: a case study of COVID-19 in Hubei Province, China

T. Chen, Y. Jin, et al.

Biology

Neuroimaging the effects of smartphone (over-)use on brain function and structure-a review on the current state of MRI-based findings and a roadmap for future research

C. Montag and B. Becker

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny