A Multi-Granularity Pattern-Based Sequence Classification Framework for Educational Data

Abstract

Abstract-In many application domains, such as education, sequences of events occurring over time need to be studied in order to understand the generative process behind these sequences, and hence classify new examples. In this paper, we propose a novel multi-granularity sequence classification framework that generates features based on frequent patterns at multiple levels of time granularity. Feature selection techniques are applied to identify the most informative features that are then used to construct the classification model. We show the applicability and suitability of the proposed framework to the area of educational data mining by experimenting on an educational dataset collected from an asynchronous communication tool in which students interact to accomplish an underlying group project. The experimental results showed that our model can achieve competitive performance in detecting the students' roles in their corresponding projects, compared to a baseline similarity-based approach.

Mining Behavioral Sequence Constraints for Classification

“…S EQUENCE mining has experienced a vast surge in interest in recent years, finding its application in numerous domains, such as bioinformatics [1], text mining [2], road analysis [3] and user behavior analysis [4]. More recently, it has also been proven useful for analyzing educational data [5].…”

Timely dropout prediction with learner behavior data

“…Since the quantity of data determines, to a large extent, the generalizability of learning patterns or trends, current VLEs harvest a plethora of activity data from diverse data sources [27]. The acquired footprint repository, therefore, encompasses the digital life of a learner and includes, for example, learning pathways, performance, and duration spent on resources (e.g., videos, notes, and questions) [28][29][30][31]. VLEs employ such activity-centric data to facilitate analysis with the aim of optimizing learning during the learning process [32].…”