Abstract
One of the challenges of an intelligent tutoring system (ITS) is adapting the difficulty level of the questions posed to the student to suit the student’s academic level. Our study examines the task of adjusting the system’s level of challenges to the level of the learner and addresses the questions of how best to do so and whether there is any benefit from such adjustment. To answer these questions, we developed reading comprehension courseware that includes three adaptive algorithms for adjusting the level of the questions presented to the students: the random selection algorithm, the Q-learning based algorithm, and the Bayesian inference algorithm. We conduct a real-world experiment in which real high school students used the courseware to improve their reading comprehension skills. In order to compare and evaluate the performance of the algorithms, the courseware used by each student utilized one of the three adaptive algorithm alternatives. Our results demonstrate that when considering all of the students, there was significant improvement (learning gain) using each of the methods.
Highlights
Intelligent tutoring systems (ITSs) are based on artificial intelligence methods that aim to teach a student specific subjects or improve particular skills [1]
The research question addressed in our study concerns how to adjust the level of challenges and practices of the system to the level of the learner and whether there is any benefit from such adjustment
We believe that the reasons for this were that performing the experiment was time consuming and students were able to stop using it at any time
Summary
Intelligent tutoring systems (ITSs) are based on artificial intelligence methods that aim to teach a student specific subjects or improve particular skills [1]. An ITS must be adaptive with respect to the student's capabilities which dynamically change over the tutoring period. Teachers often face a dilemma in knowing how best to engage students and foster their academic achievement without discouraging them by presenting challenges that students perceive as too difficult [1], [3]. The same dilemma exists when designing a courseware capable of adapting itself to the student's level. In this research we aim to develop courseware that presents questions which are suited to the student’s academic level, encouraging the student to advance academically and enabling the student to realize his/her potential without causing frustration or discouragement. Previous studies [4]-[8] have considered this problem and suggested several methods of dealing with it
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
