Proposal on discussion element-specific deliberation based on autonomous agent facilitation for consensus building in complex society
| Project/Area Number |
22K17948
|
|---|
| Research Category |
Grant-in-Aid for Early-Career Scientists
|
| Allocation Type | Multi-year Fund |
|---|
| Review Section |
Basic Section 61030:Intelligent informatics-related
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
SAHAB Sofia 京都大学, 情報学研究科, 特定助教 (00892928)
|
|---|
| Project Period (FY) |
2022-04-01 – 2025-03-31
|
| Project Status |
Granted (Fiscal Year 2023)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2024: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
Fiscal Year 2023: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2022: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | AI agent policy / Conversational agent / Targeted facilitation / IBIS framework / Idea generation / Issue generation / Online discussion / consensus policy / conversational agent / online discussion / agent facilitation / cyber democracy |
|---|
| Outline of Research at the Start |
In this project, facilitation consensus policy subclass is constructed for agent to lead discussion. Three aspects are included: consensus policy during first phase of discussion for social issue prioritization; consensus policy after need assessment for issue-solving; and consensus policy for pros of idea and cons of idea. Based on this method, proactive agent will characterize conversational agent to start from raising issue-prioritization, move with issue-solving mediation, and ends with argument over identified ideas pros and cons deliberation.
|
| Outline of Annual Research Achievements |
Building upon the developed element-specific facilitation policy based on the Issue-Based Information System (IBIS), several social and controlled experiments were conducted. The results of these experiments, submitted to national and international journals and conferences, compared different types of facilitation. For example, one experiment compared targeted facilitation, where the conversation agent prompted participants to generate issues related to the discussion theme, with general facilitation, showing that the former led to a higher number of objections raised during discussions. Another experiment compared the same type of targeted facilitation with no facilitation, revealing that the targeted facilitation approach promoted the generation of new ideas.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
The research has progressed smoothly, with all experiments completed and results analyzed. Efforts are currently focused on further analyzing the results to revise the facilitation policy and settings for potentially improved outcomes.
|
| Strategy for Future Research Activity |
The research project will proceed with further analysis of the results to refine the facilitation policy and settings. Efforts will be made to conduct additional experiments to test these refined approaches and assess their impact. New avenues for research within the framework of the Issue-Based Information System (IBIS) will be explored, with a focus on enhancing intergroup communication and understanding.
|
Report
(2 results)
Research Products
(12 results)
