2023 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 – 2025-03-31
|
| Keywords | machine learning / EFL / learning styles / affordances / education / ICT |
|---|
| Outline of Annual Research Achievements |
The main goal of this study is to investigate learning styles in the context of English as a Foreign Language education, employing Machine Learning techniques to detect changes in the learning styles of online students. An essential intermediate step involves understanding the relationship between device choice and a range of learning activities. Once this understanding is established, it will enable a more comprehensive analysis of different content delivery methods. During the 2023 academic year, we utilized a variety of qualitative coding approaches and Principal Component Analysis (PCA) based methods for data analysis. THe research was published multiple academic proceedings, Journal articles, and book chapters.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
This year, we successfully surveyed a broader participant pool about their educational device preferences, strengthening our research's empirical foundation. We rigorously analyzed the data to understand students' online learning perceptions, which will improve the interpretation of our final results. Additionally, we investigated the role of generative AI in creating personalized learning content and adapting to individual learning styles within the context of EFL education. We also explored major obstacles to implementing online education, considering historical strategies to predict potential technical problems during our remaining research. Consequently, the main objectives were achieved, leading to the choice of Option 2.
|
| Strategy for Future Research Activity |
The research plan for the 2024 academic year will primarily focus on collecting more extensive data on learning styles and integrating generative AI to create personalized learning experiences within English as a Foreign Language (EFL) education.
Following the expanded data collection phase, a thorough analysis of the learning styles data will be performed using Principal Component Analysis (PCA) based techniques, which were successfully applied during the 2022 academic year research. The research will also investigate the potential of generative AI in creating adaptive learning content tailored to individual learning styles, enhancing the effectiveness of EFL education.
|
| Causes of Carryover |
The 2024 research plan allocates funds for conference attendance, enabling the presentation of findings and fostering academic collaborations. Resources will be dedicated to purchasing relevant books and materials to support the investigation of learning styles and generative AI in EFL education. The budget will also cover expenses related to data collection, analysis software, and any necessary technical infrastructure. Careful financial planning will ensure the efficient use of funds throughout the research process.
|
