. We use educational data mining to arrive at models of help-seeking behaviors associated with learning from datasets from three countries: Costa Rica, the Philippines, and the USA. The models were then tested on each country’s data to find out how effective help-seeking behavior varies across countries. This study found that models of effective help-seeking are not necessarily transferrable ac...

Researchers use many different metrics for evaluation of performance of student models. The aim of this paper is to provide an overview of commonly used metrics, to discuss properties, advantages, and disadvantages of different metrics, to summarize current practice in educational data mining, and to provide guidance for evaluation of student models. In the discussion we mention the relation of...

Dynamic assessment (DA) has been advocated as an interactive approach to conduct assessments to students in the learning systems as it can differentiate student proficiency at a finer grained level. Sternberg and others have been pursuing an alternative to IQ tests. They proposed to give students tests to see how much assistance it takes a student to learn a topic; and to use as a measure of th...

How should a wide variety of educational activities be sequenced in order to maximize student learning? We recently proposed the Sequencing Constraint Violation Analysis (SCOVA) method to help address this question. In this paper, we propose how SCOVA could be transformed into a workflow in LearnSphere so that other researchers and practitioners can find answers to the aforementioned question i...

Automated techniques have proven useful for improving models of student learning even beyond the best human-generated models. There has been concern among the EDM community about whether small prediction improvements matter. We argue that they can be quite significant when they are interpretable and actionable, but the importance of generating meaningful, validated, and generalizable interpreta...

Two of the major goals in Educational Data Mining are determining students’ state of knowledge and determining whether students are affectively engaged with the task and in positive affective states. These two problems are usually examined separately and multiple methods have been proposed to solve each of them. However, little work has been done on tracing both of these states in parallel and ...

<p>The main purpose of this research paper is to analyze the moodle data and identify most influencing features develop predictive model. The applies a wrapper-based feature selection method called Boruta for best predicting features. Data were collected from eighty-one students who enrolled in course Human Computer Interaction (COMP341), offered by Department Science Engineering at Kathm...

This study investigates ways to interpret and utilize the vast amount of log data collected from an educational game called Refraction to understand student fraction learning. Study participants are elementary students enrolled in an online virtual school system who played the game over the course of multiple weeks. Findings suggest that students use a variety of splitting strategies when solvi...