E2Vec: Feature Embedding with Temporal Information for Analyzing Student Actions in E-Book Systems

TL;DR

E2Vec is a new embedding method that captures temporal information from student interaction logs in e-book systems, improving analysis of student behaviors and at-risk detection.

Contribution

It introduces a word embedding-based approach that incorporates time intervals into feature representations of student activity logs.

Findings

E2Vec effectively captures temporal learning behavior differences.

The method improves at-risk student detection performance.

Demonstrates potential for generalizability across datasets.

Abstract

Digital textbook (e-book) systems record student interactions with textbooks as a sequence of events called EventStream data. In the past, researchers extracted meaningful features from EventStream, and utilized them as inputs for downstream tasks such as grade prediction and modeling of student behavior. Previous research evaluated models that mainly used statistical-based features derived from EventStream logs, such as the number of operation types or access frequencies. While these features are useful for providing certain insights, they lack temporal information that captures fine-grained differences in learning behaviors among different students. This study proposes E2Vec, a novel feature representation method based on word embeddings. The proposed method regards operation logs and their time intervals for each student as a string sequence of characters and generates a student vector of learning activity features that incorporates time information. We applied fastText to generate an embedding vector for each of 305 students in a dataset from two years of computer science courses. Then, we investigated the effectiveness of E2Vec in an at-risk detection task, demonstrating potential for generalizability and performance.