|
Title:
|
INTELLIGENT TUTORING SYSTEMS MEET GENERATIVE-AI CHATBOTS TO CRAFT PERSONALIZED LEARNING PATHS: A PHENOMENOLOGICAL STUDY REVEALS 7 KEY DESIGN ISSUES |
|
Author(s):
|
Michele Norscini, Lucio Monterubbiano and Chiara Moroni |
|
ISBN:
|
978-989-8704-72-6 |
|
Editors:
|
Demetrios G. Sampson, Dirk Ifenthaler and Pedro Isaías |
|
Year:
|
2025 |
|
Edition:
|
Single |
|
Keywords:
|
Intelligent Tutoring System, Large Language Model, Chatbot, Learning, Think-aloud, Phenomenology |
|
Type:
|
Short Paper |
|
First Page:
|
387 |
|
Last Page:
|
391 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
if you are a member please login 
|
|
Paper Abstract:
|
In asynchronous online learning, integrating Large Language Models (LLMs) into Intelligent Tutoring Systems (ITSs)
opens up new possibilities for delivering conversational support to guide learners through content-rich course libraries.
In this study, we present a phenomenological investigation of user experiences with a generative-AI-powered chatbot
capable of recommending a personalized learning path at the end of an exploratory conversation. Using the think-aloud
protocol, we collected data on users' interactional experiences, and through phenomenological analysis, we explored their
perceptions and expectations.
Findings indicate overall user satisfaction with the chatbot's ability to provide tailored orientation within an extensive
training library, particularly in terms of interactional fluency and personalization. Nonetheless, each participant
highlighted at least one critical issueranging from unclear recommendation logic and occasional mismatches to
limitations in planning support and concerns about tone or metaphor use.
Building on these insights, we identified seven key design issues that should inform the development of educational
conversational agents. |
|
|
|
|
|
|
