Our learning-by-teaching environment, Betty's Brain, captures a wealth of data on students' learning interactions as they teach a virtual agent. This paper extends an exploratory data mining methodology for assessing and comparing students' learning behaviors from these interaction traces. The core algorithm employs sequence mining techniques to…

Student modeling plays a critical role in developing and improving instruction and instructional technologies. We present a technique for automated improvement of student models that leverages the DataShop repository, crowd sourcing, and a version of the Learning Factors Analysis algorithm. We demonstrate this method on eleven educational…

Although learning from multiple representations has been shown to be effective in a variety of domains, little is known about the mechanisms by which it occurs. We analyzed log data on error-rate, hint-use, and time-spent obtained from two experiments with a Cognitive Tutor for fractions. The goal of the experiments was to compare learning from…

In recent years, the usefulness of affect detection for educational software has become clear. Accurate detection of student affect can support a wide range of interventions with the potential to improve student affect, increase engagement, and improve learning. In addition, accurate detection of student affect could play an essential role in…

A long-standing challenge for knowledge tracing is how to update estimates of multiple subskills that underlie a single observable step. We characterize approaches to this problem by how they model knowledge tracing, fit its parameters, predict performance, and update subskill estimates. Previous methods allocated blame or credit among subskills…

Identifying the skills that determine the success or failure to exercises and question items is a difficult task. Multiple skills may be involved at various degree of importance, and skills may overlap and correlate. In an effort towards the goal of finding the skills behind a set of items, we investigate two techniques to determine the number of…

This paper proposes to the use of a meta-learning approach for automatic parameter tuning of a well-known decision tree algorithm by using past information about algorithm executions. Fourteen educational datasets were analysed using various combinations of parameter values to examine the effects of the parameter values on accuracy classification.…

The goal of this paper is to use Knowledge Tracing to augment the results obtained from an experiment that investigated the effects of practice schedules using an intelligent tutoring system for fractions. Specifically, this experiment compared different practice schedules of multiple representations of fractions: representations were presented to…

This paper proposes a classification via clustering approach to predict the final marks in a university course on the basis of forum data. The objective is twofold: to determine if student participation in the course forum can be a good predictor of the final marks for the course and to examine whether the proposed classification via clustering…

In recent years, machine-learning software packages have made it easier for educational data mining researchers to create real-time detectors of cognitive skill as well as of metacognitive and motivational behavior that can be used to improve student learning. However, there remain challenges to overcome for these methods to become available to…

We have assembled a large corpus of student submissions to an automatic grading system, where the subject matter involves the translation of natural language sentences into propositional logic. Of the 2.3 million translation instances in the corpus, 286,000 (approximately 12%) are categorized as being in error. We want to understand the nature of…

In recent years, the educational data mining and user modeling communities have been aggressively introducing models for predicting student performance on external measures such as standardized tests as well as within-tutor performance. While these models have brought statistically reliable improvement to performance prediction, the real world…