Learning Path Recommendation System for Programming Education Based on Neural Networks

Programming education has recently received increased attention due to growing demand for programming and information technology skills. However, a lack of teaching materials and human resources presents a major challenge to meeting this demand. One way to compensate for a shortage of trained teache...

Full description

Saved in:
Bibliographic Details
Published in:International journal of distance education technologies 2020-01, Vol.18 (1), p.36-64
Main Authors: Saito, Tomohiro, Watanobe, Yutaka
Format: Article
Language:English
Subjects:
Academic Ability
Charts
Classification
Computer Assisted Instruction
Computer Science Education
Computer Software
Core curriculum
Data Analysis
Distance learning
Education
Electronic Learning
Equipment and supplies
Human Resources
Information Technology
Instructional Materials
Learning Processes
Machine learning
Management Systems
Neural networks
Online Systems
Prediction
Prediction models
Problem Solving
Programming
Recommender systems
Recurrent neural networks
Scores
Short Term Memory
Teaching
Teaching Methods
Visualization
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Programming education has recently received increased attention due to growing demand for programming and information technology skills. However, a lack of teaching materials and human resources presents a major challenge to meeting this demand. One way to compensate for a shortage of trained teachers is to use machine learning techniques to assist learners. This article proposes a learning path recommendation system that applies a recurrent neural network to a learner's ability chart, which displays the learner's scores. In brief, a learning path is constructed from a learner's submission history using a trial-and-error process, and the learner's ability chart is used as an indicator of their current knowledge. An approach for constructing a learning path recommendation system using ability charts and its implementation based on a sequential prediction model and a recurrent neural network, are presented. Experimental evaluation is conducted with data from an e-learning system.
ISSN:1539-3100
1539-3119
DOI:10.4018/IJDET.2020010103