In this paper we discuss how machine learning, and specifical ly how naive Bayes classifiers, can be used for user modeling tasks. We argue that in g eneral, machine learning techniques should be used to improve a user modeling system’ s interactions with users. We further argue that a naive Bayes classifier is a reasonable ap pro ch to many user modeling problems, given its advantages of quick learning and low com putational overhead. These are critical features for an online user modeling system. We discuss two such user modeling systems and how this technique can be applied to them. F inally, we propose a set of enhancements to naive Bayes classifiers to improve their p r dictive accuracy, and allow them to better adapt to the user’s performance. Our eventual goal is to construct a learning system that requires no intervention from the designer othe r than a list of potentially useful features.
[1]
Igor Kononenko,et al.
Semi-Naive Bayesian Classifier
,
1991,
EWSL.
[2]
Richard S. Sutton,et al.
Introduction to Reinforcement Learning
,
1998
.
[3]
Pat Langley,et al.
Induction of Selective Bayesian Classifiers
,
1994,
UAI.
[4]
Michael J. Pazzani,et al.
Searching for Dependencies in Bayesian Classifiers
,
1995,
AISTATS.
[5]
Jim Kurose,et al.
Intelligence on the Web
,
1997
.
[6]
Joseph E. Beck,et al.
Using a Learning Agent with a Student Model
,
1998,
Intelligent Tutoring Systems.
[7]
Daniel Billsus,et al.
Learning Probabilistic User Models
,
1998
.
[8]
Joseph E. Beck,et al.
Using the Student Model to Control Problem Difficulty
,
1997
.
[9]
Pat Langley,et al.
An Analysis of Bayesian Classifiers
,
1992,
AAAI.