2024 Fiscal Year Research-status Report
From designing adaptive facilitation threshold to summarization timeline based on IBIS: Democratizing discussion in online education conversation
| Project/Area Number |
23K17164
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2023-04-01 – 2027-03-31
|
| Keywords | Online Discussion / User Behaviour Studies / Conversational agents / Deliberation / Group Interactions / Online learning |
|---|
| 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.
|
| Causes of Carryover |
An amount of 86,878円 remained unused at the end of the fiscal year because I had planned to purchase specific software in late March. However, due to the proximity to the fiscal year closing period, the procurement could not be processed in time.
The amount will be used in the next fiscal year to complete the intended software purchase necessary for ongoing research and project activities.
|
