Back to search

University of British Columbia

Personalizing explanations of AI hints based on user characteristics in an intelligent tutoring system

Abstract

dc:description

Explainable AI (XAI) refers to having artificial intelligence-based systems provide understandable explanations or justifications for their decisions, predictions, or actions. In essence, XAI seeks to demystify the opaque nature of AI models, allowing humans to comprehend the reasoning behind AI-driven outcomes. While such explanations are beneficial in general, the need and effectiveness of the explanations might depend on application-dependent factors and user differences. In this thesis, we investigate personalizing the explanations that an Intelligent Tutoring System (ITS) generates to justify the hints it provides to students to foster their learning. The personalization targets students with low levels of two traits, Need for Cognition and Conscientiousness, and aims to enhance these students’ interaction with the explanations, based on prior findings that these students do not naturally engage with the explanations but would benefit from them if they do. To evaluate the effectiveness of the personalization, we conducted a user study where we found that our proposed personalization significantly increased our target users’ interaction with the hint explanations and their learning. Hence, this work provides insights into personalizing AI-driven explanations for learning which is arguably a cognitively demanding task. Furthermore, to gain initial insights on if and how hint explanations should be personalized based on the user’s state of confusion about the hints, we conducted an exploratory study using the same ITS. The goal of this study was to see if and how users rely on explanations when they are confused about the AI hints. However, no user in the study reported confusion on ACSP hints indicating the need for further investigation of the potential role of short-term user states on explanation effectiveness.

Degree

thesis:*
Name thesis:degree_name
Master of Science - MSc
Level thesis:degree_level
master's
Discipline thesis:degree_discipline
Computer Science
Grantor dc:publisher
University of British Columbia
Year dc:date
2024

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Bahel, Vedant Rajesh
Contributors dc:contributor
  • Conati, Cristina

Rights

dc:rights
Statement dc:rights
  • Attribution-NonCommercial-NoDerivatives 4.0 International
Language dc:language
eng

Identifiers

dc:identifier.*
Handle dc:identifier
http://hdl.handle.net/2429/88387

Chain of custody

source
Harvested from
University of British Columbia
Base URL
circle.library.ubc.ca/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
related terms
citation

Bahel, Vedant Rajesh. Personalizing explanations of AI hints based on user characteristics in an intelligent tutoring system. master's thesis, University of British Columbia, 2024. http://hdl.handle.net/2429/88387