Online Program Home
My Program

Abstract Details

Activity Number: 131
Type: Contributed
Date/Time: Monday, August 1, 2016 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Learning and Data Science
Abstract #318856 View Presentation
Title: E-Learning Data Analysis for Building a Personalized Recommendation System
Author(s): Shuang Liu* and K.F. LAM
Companies: and The University of Hong Kong
Keywords: educational data mining ; item response theory ; personalized recommendation system

Currently, the increase of online learning system makes students' performance tangible and measurable. The database that the online learning systems provide can record students' trace of learning simultaneously and can be accessed and analyzed by researchers. This gives us a chance to improve our teaching quality by building a personalized recommendation system by taking into consideration of individual student's learning ability and habit. We propose a three-step recommendation strategy to recommend suitable learning material, such as quizzes and videos, for individual student. Firstly, we analyze students' performance using Item Response Theory (Baker et al., 2004) to estimate individual student's ability, and the level of difficulty of the quizzes. Secondly, we investigate the learning pattern of the high ability students whom are to be identified in the first step through mining activities sequence by the AprioriAll algorithm (Agrawal and Srikant, 1995). Eventually, we accomplish personalized recommendation to all students based on the combination of students' own ability and the good practice pattern of the high ability students.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association