High-Level Student Modeling with Machine Learning

Abstract

Abstract. We have constructed a learning agent that models student behavior at a high level of granularity for a mathematics tutor. Rather than focusing on whether the student knows a particular piece of knowledge, the learning agent determines how likely the student is to answer a problem correctly and how long he will take to generate this response. To construct this model, we used traces from previous users of the tutor to train the machine learning agent. This agent used information about the student, the current topic, the problem, and the student's efforts to solve this problem to make its predictions. This model was very accurate at predicting the time students required to generate a response, and was somewhat accurate at predicting the likelihood the student's response was correct. We present two methods for integrating such an agent into an intelligent tutor.

Data mining in course management systems: Moodle case study and tutorial

“…At the same time, regression analyses have been used to predict a student's knowledge and which metrics help to explain the poor prediction of state exam scores (Feng, Heffernan, & Koedinger, 2005). Regression has also been applied for predicting whether the student will answer a question correctly enough (Beck & Woolf, 2000), and for predicting end-of-year accountability assessment scores (Anozie & Junker, 2006). …”

Effect of Bayesian Student Modeling on Academic Achievement in Foreign Language Teaching (University Level English Preparatory School Example)

“…Considering that the student modeling process is itself a diagnosis problem (Yudelson, Medvedeva, & Crowley, 2008), it is not surprising to see machine learning mechanisms build in student modeling layers of many studies (Aslan & İnceoglu, 2007;Tsiriga & Virvou, 2004). There are four mains problems to be addressed when machine learning is used with a student modeling system: the need for a large amount of data (Beck & Woolf, 2000), computational complexity, the crucial need for tagged data, and the concept drift problem (Webb, Pazzani, & Billsus, 2001). …”

Predicting Students’ Academic Performances – A Learning Analytics Approach using Multiple Linear Regression

“…[36] identified variables that could predict success in college courses using multiple regression while [37], used regression and decision trees analysis for predicting university students" satisfaction. Linear regression was used for predicting exam results in distance education courses [38], for predicting end-of-year accountability assessment scores [39] and also for predicting the probability that the student"s next response is correct [40]. Logistic regression was used for predicting when a student will get a question correct and association rules to guide a search process to find transfer models to predict a student"s success [41].…”