Abstract

Learners are expected to stay wakeful and focused while interacting with e-learning platforms. Although wakefulness of learners strongly relates to educational outcomes, detecting drowsy learning behaviors only from log data is not an easy task. In this study, we describe the results of our research to model learners’ wakefulness based on multimodal data generated from heart rate, seat pressure, and face recognition. We collected multimodal data from learners in a blended course of informatics and conducted two types of analysis on them. First, we clustered features based on learners’ wakefulness labels as generated by human raters and ran a statistical analysis. This analysis helped us generate insights from multimodal data that can be used to inform learner and teacher feedback in multimodal learning analytics. Second, we trained machine learning models with multiclass-Support Vector Machine (SVM), Random Forest (RF) and CatBoost Classifier (CatBoost) algorithms to recognize learners’ wakefulness states automatically. We achieved an average macro-F1 score of 0.82 in automated user-dependent models with CatBoost. We also showed that compared to unimodal data from each sensor, the multimodal sensor data can improve the accuracy of models predicting the wakefulness states of learners while they are interacting with e-learning platforms.

Highlights

  • IntroductionE-learning has grown rapidly due to advances in information technologies

  • In recent years, e-learning has grown rapidly due to advances in information technologies

  • We classified all features based on three wakefulness levels (Asleep vs. Drowsy vs. Awake) and we ran Friedman’s test, and post hoc tests (Scheffe’s test)

Read more

Summary

Introduction

E-learning has grown rapidly due to advances in information technologies. In face-to-face learning contexts, teachers can often identify learners’ internal states, such as engagement, boredom, concentration, and wakefulness, and are able to adapt their pedagogical approaches and teaching materials/methods . In e-learning settings, real-time adaptation is not easy due to physical distance and asynchrony To address this problem, prediction methods are used to infer a variable based on other variables extracted from learning log data, such as response times to predict engagement [11] and conversational cues to predict affective states of boredom, confusion, flow, and frustration [12]. Wakefulness during online coursework can be considered an instance of behavioral engagement and essential to ensure improved learning outcomes. This type of behavioral engagement is largely under-researched in learning contexts

Objectives
Methods
Results
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call