Exploring the mechanisms of AI message generation: A chatbot development activity for students

Abstract

Courses

Health Communication, Public Communication Campaigns, Public Relations, Introduction to Communication.

Objectives

By the end of this workshop, students will be able to: (1) understand how artificial intelligence–based large language learning models work and be able to explain core concepts such as word embeddings, neural networks, and prompting; and (2) apply what they have learned by building and improving an expert health chatbot. Overall, the workshop aims to empower students with the necessary knowledge to use rapidly advancing artificial intelligence responsibly for health communication.

Notes

1 Jupyter notebooks blend textbook-style explanations with executable code cells. They have become immensely popular as a platform for teaching computational skills, especially to newcomers who would struggle with installations and writing the code. Instead, notebooks allow users to run prewritten code, inspect the results, and learn by changing the code (Kluyver et al., 2016).

2 The lecture slides with resources and the code templates (Jupyter notebooks) used for the Build-a-Bot workshop are available online at https://github.com/nomcomm/communication_teacher_nlg.