Learning Support by Novel Modality Process Analysis of Educational Big Data
| Project/Area Number |
21K19824
|
|---|
| Research Category |
Grant-in-Aid for Challenging Research (Exploratory)
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Medium-sized Section 62:Applied informatics and related fields
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
久富 望 京都大学, 教育学研究科, 助教 (70825992)
|
|---|
| Project Period (FY) |
2021-07-09 – 2025-03-31
|
| Project Status |
Granted (Fiscal Year 2023)
|
| Budget Amount *help |
¥6,370,000 (Direct Cost: ¥4,900,000、Indirect Cost: ¥1,470,000)
Fiscal Year 2022: ¥2,600,000 (Direct Cost: ¥2,000,000、Indirect Cost: ¥600,000)
Fiscal Year 2021: ¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
|
|---|
| Keywords | self-explanation / real-time feedback / data generation / automated scoring / Modality analysis / Learning process / Learning Analytics / Recommendation / Knowledge Map / Modality Analysis / Learning Process |
|---|
| Outline of Research at the Start |
Learners often get stuck or fail a task during the process of learning a new skill or knowledge. This research investigates a novel analysis method from multi source data of learner modality combined with reading behavior and knowledge mapping to predict the plateau in the mastery of prerequisites.
|
| Outline of Annual Research Achievements |
The self-explanation real-time feedback and recommender system was developed, and an experiment was conducted in a school to determine it's usefulness. The system focused on providing timely feedback to students who has completed the self-explanation task. The results of this were publised as an article in an international journal. However, some additional problems were found during the development and evaluation, namely: the lack of data for traning feedback and scoring models, and issues with being able to provide sample self-explanations to students as feedback. We investigated using LLMs to generate additional datasets and found that this could enhance the traininng and accuracy of self-explanation scoring models, and disseminated these as articles in an international journal.
|
| Current Status of Research Progress |
Current Status of Research Progress
3: Progress in research has been slightly delayed.
Reason
Additional issues were found when evaluating a self-explanation real-time feedback system, and this has widened our investigation to include data generation and sample self-explanation example generation, which has extended the overall duration of the research project.
|
| Strategy for Future Research Activity |
The results of the real-time self-explanation feedback system has also bought about data issues that have been examined to an extent, and this will be used to revised the feedback and scoring system. We plan to conduct an additional evaluation on this and anticipate in writing several journal and international conference papers to disseminate the findings to the broader research community.
|
Report
(3 results)
Research Products
(21 results)
