English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Large-Language Models like GPT-3 have the potential to enable HCI designersand researchers to create more human-like and helpful chatbots for specificapplications. But evaluating the feasibility of these chatbots and designingprompts that optimize GPT-3 for a specific task is challenging. We present acase study in tackling these questions, applying GPT-3 to a brief 5-minutechatbot that anyone can talk to better manage their mood. We report arandomized factorial experiment with 945 participants on Mechanical Turk thattests three dimensions of prompt design to initialize the chatbot (identity,intent, and behaviour), and present both quantitative and qualitative analysesof conversations and user perceptions of the chatbot. We hope other HCIdesigners and researchers can build on this case study, for other applicationsof GPT-3 based chatbots to specific tasks, and build on and extend the methodswe use for prompt design, and evaluation of the prompt design.

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