Power of Attention in MOOC Dropout Prediction

Shengjun Yin,Leqi Lei,Hongzhi Wang,Wentao Chen

doi:10.1109/access.2020.3035687

Shengjun Yin, Leqi Lei + Show 2 more

Open Access

https://doi.org/10.1109/access.2020.3035687

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2020
Citations: 24	License type: CC BY 4.0

Affiliation: Harbin Institute of Technology

Abstract

The dropout rate of massive open online courses (MOOC) has been significantly high, which makes its prediction an important problem. In this article, we try to transfer the knowledge gained in the field of Natural Language Processing into the field of MOOC dropout prediction, due to the high similarity between them. More specifically, we attempt to study and show the powerful use of attention and conditional random field, both of which have been very popular architectures when solving NLP problems. A novel neural network structure is designed as the combination of these techniques. Extensive experimental results demonstrate that the proposed approach is effective.

Highlights

M ASSIVE Open Online Courses (MOOC for brief), is a concept of a large number of courses online and accessible to everyone, no matter where, who and when
Since studying online cost little based on the fact that most courses on the massive open online courses (MOOC) platform are free, and there are usually no supervisors to push the learners, and last but not least, no punishment is for dropping out the course
Making accurate and effective predictions can help much to manage the course on MOOC, and corresponding measures can be taken to strengthen the learning will of the learner

Summary

Introduction

M ASSIVE Open Online Courses (MOOC for brief), is a concept of a large number of courses online and accessible to everyone, no matter where, who and when. A prominent problem of MOOC since its day of birth is the rather high dropout rate [4]. Since studying online cost little based on the fact that most courses on the MOOC platform are free, and there are usually no supervisors to push the learners, and last but not least, no punishment is for dropping out the course. Making accurate and effective predictions can help much to manage the course on MOOC, and corresponding measures can be taken to strengthen the learning will of the learner. Some of them have achieved high accuracy on specific scenarios [5]

Objectives

Results

Conclusion