权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Using Machine Learning to Identify Learner Styles across Devices in Online EFL Lessons

使用机器学习来识别在线英语课程中跨设备的学习者风格

基本信息

批准号：
20K00862
负责人：
イリチュピーター
金额：
$ 2.66万
依托单位：
The University of Aizu
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (C)
财政年份：
2020
资助国家：
日本
起止时间：
2020-04-01 至 2024-03-31
项目状态：
已结题

来源：
https://kaken.nii.ac.jp/en/grant/KAKENHI-PROJECT-20K00862/
关键词：
Machine Learning (ML)EFL Learning styles Affordances Education EFL Education Machine Learning Learning Styles EFL education

项目摘要

The primary objective of this research is to scrutinize learning styles within the sphere of English as a Foreign Language (EFL) education, utilizing Machine Learning (ML) to identify alterations in the learning styles of online students. A critical intermediate phase involves comprehending the correlation between the choice of device and an array of learning activities. Once established, this comprehension will facilitate a more detailed examination of various modes of content delivery. Throughout the academic year of 2022, we deployed an assortment of qualitative coding techniques and PCA-based methodologies for data analysis, while also furthering our investigation into the role of device usage in education, specifically analyzing student device preferences in an online learning environment.The findings derived from our 2022 research have been disseminated at multiple academic conferences with published proceedings, including FIE 2022, EDUNINE2022, EUROCALL 2022, and LWMOOCS 2022. A special issue of the IEEE Transactions in Education featured an extended version of one of these conference proceedings. Our preliminary findings also received acceptance for an extended publication in the same special issue of IEEE Transactions in Education. Additionally, two book proposals have been approved for publication: one by Springer and the second by IGI Global, with the latter featuring a comprehensive range of expertise from the fields of education and engineering.

本研究的主要目的是仔细研究英语作为外语（EFL）教育领域的学习风格，利用机器学习（ML）来识别在线学生学习风格的变化。一个关键的中间阶段包括理解设备的选择和一系列学习活动之间的关系。一旦建立起来，这种理解将有助于更详细地检查各种内容交付模式。在整个2022学年，我们部署了各种定性编码技术和基于pca的数据分析方法，同时也进一步调查了设备使用在教育中的作用，特别是分析了学生在在线学习环境中的设备偏好。我们2022年的研究结果已在多个学术会议上发表，包括FIE 2022、EDUNINE2022、EUROCALL 2022和LWMOOCS 2022。《IEEE教育汇刊》（IEEE Transactions in Education）的一期特刊刊载了其中一篇会议论文集的扩展版。我们的初步发现也在IEEE教育汇刊的同一期特刊上获得了扩展出版的接受。此外，两本书的出版建议已被批准：一本由施普林格出版，另一本由IGI Global出版，后者以教育和工程领域的全面专业知识为特色。

项目成果

期刊论文数量（30）

专著数量（0）

科研奖励数量（0）

会议论文数量（0）

专利数量（0）

Mapping the Digital Ecosystem for Education

绘制教育数字生态系统

DOI：
10.1109/econf51404.2020.9385479
发表时间：
2020
期刊：
IEEE Xplore Proceedings of 2020 Sixth International Conference on e-Learning
影响因子：
0
作者：
Kluge;D.;Peter Ilic
通讯作者：
Peter Ilic

Sentiment analysis of students’ attitudes toward mobile learning activities

学生对移动学习活动态度的情感分析

DOI：
10.14705/rpnet.2020.48.1174
发表时间：
2020
期刊：
CALL for widening participation: short papers from EUROCALL 2020
影响因子：
0
作者：
Eiichiro Tsutsui;Kirara Nagahashi;Kazumi Nishimura;Kazuharu Owada;中谷安男;石崎博志;Peter Ilic
通讯作者：
Peter Ilic

The Challenge of Information and Communications Technology in Education

信息和通信技术在教育中的挑战