2021 Fiscal Year Research-status Report
Using Machine Learning to Identify Learner Styles across Devices in Online EFL Lessons
| Project/Area Number |
20K00862
|
|---|
| Research Institution | The University of Aizu |
|---|
Principal Investigator |
イリチュ ピーター 会津大学, コンピュータ理工学部, 准教授 (10511503)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
Debopriyo Roy 会津大学, コンピュータ理工学部, 教授 (30453020)
|
|---|
| Project Period (FY) |
2020-04-01 – 2023-03-31
|
| Keywords | EFL Education / Machine Learning / Learning Styles |
|---|
| Outline of Annual Research Achievements |
The goal of this research is to investigate learning styles in EFL education by using Machine Learning (ML) to identify online learner style changes. This 2021 academic year, qualitative coding techniques and KPCA ML technique were used to analyze data. Also, we surveyed device use for education, analyzed student device preferences for online learning, investigated the emergency implementing of online education. The results of this research in the 2021 academic year have been presented at several conferences with published proceedings, including ECONF2021, ETLTC2021, Mobile learning 2022, and the VI IEEE WEEC2022. Preliminary findings have been accepted for publication in a book chapter to be published by Springer and a chapter published by IGI.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
During this year, we successfully continued the application of KPCA ML technique to analyze sets of high-dimensional data to ensure the technique is robust enough to deal with the data needed for this research. Also, we surveyed more participants on their preferred device use for education to gather device data that will be included in the research. In addition, we analyzed data to determine student perceptions of online learning, which will aid in the interpretation of the final results. And we investigated key challenges to implementing online education, considering historical approaches to help foresee any technical issues that may arise over the remainder of the research period. So, the main goals were achieved, so option 2 was selected.
|
| Strategy for Future Research Activity |
Based on these results, in the 2022 academic year, the research can proceed to focus on further data collection, specifically of learning styles data. Following this, the data on learning styles will be analyzed using the KPCA technique tested during the 2021 academic year’s research.
|
| Causes of Carryover |
Due to the COVID crisis, travel to international and domestic conferences was not possible, so the amount of travel funds used was considerably lower than predicted. Therefore the funds will be used in the next fiscal year. This amount will be used for the purchase of books and equipment required for basic research and numerical experiments.
|
Research Products
(8 results)
