| Project/Area Number |
23K17164
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 90020:Library and information science, humanistic and social informatics-related
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2023-04-01 – 2027-03-31
|
| Project Status |
Granted (Fiscal Year 2024)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2026: ¥260,000 (Direct Cost: ¥200,000、Indirect Cost: ¥60,000)
Fiscal Year 2025: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
Fiscal Year 2024: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2023: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | Online Discussion / User Behaviour Studies / Conversational agents / Deliberation / Group Interactions / Online learning / Discussion Summarization / Informed Discussions / IBIS / Conversational Agent / Conversational Agents |
|---|
| Outline of Research at the Start |
In this study, 1)I will develop facilitation messages database to enhance automated agent posted facilitation messages). 2)Then, I plan to propose an adaptive facilitation approach to enhance conversational agent facilitation threshold behavior. 3) Third, I will develop a discussion summarizations timeline based on Issue-based Information System (IBIS) to facilitated more informed engagement. 4) Finally, I will establish an analytical model using S-O-R framework to verify proposed Tasks (T1-T3) while conducting social experiments.
|
| Outline of Annual Research Achievements |
Conducted research on automated agents to enhance interactive discussions and support online education.
Evaluated LLM-based agents in online group discussions through human-agent interaction studies.
Presented findings at national and international conferences.
Explored GPT-4 as a conversational agent and considered LLMapps as a novel service in education.
Co-authored 2 journal papers and 9 conference proceedings this year, including 5 as first author.
|
| Current Status of Research Progress |
Current Status of Research Progress
1: Research has progressed more than it was originally planned.
Reason
This year, we evaluated the effectiveness of AI-assisted conversational agents in the role of discussion facilitators for online education. The research successfully met its initial objectives, and the findings were presented at both national and international conferences.
|
| Strategy for Future Research Activity |
This year, I plan to conduct a series of studies and experiments to evaluate the effectiveness of agent-based facilitation in online discussions. I will analyze and assess the agents' possible role playing position and performance in online education context. Additionally, building on previous findings, I intend to design new facilitation strategies utilizing emerging technologies, such as task-oriented conversational agents powered by large language models (LLMs). I intend to apply LLMs like GPT-4 as a conversational agent in an educational context for downstream domains. I will also conduct experiments to evaluate the efficiency of these strategies in supporting online educational dialogues.
|
