| 研究課題/領域番号 |
20K11936
|
|---|
| 研究種目 |
基盤研究(C)
|
| 配分区分 | 基金 |
|---|
| 応募区分 | 一般 |
|---|
| 審査区分 |
小区分61030:知能情報学関連
|
|---|
| 研究機関 | 京都大学 |
|---|
研究代表者 |
Rafik Hadfi 京都大学, 情報学研究科, 特定准教授 (30867495)
|
|---|
| 研究分担者 |
伊藤 孝行 名古屋工業大学, 工学(系)研究科(研究院), 教授 (50333555)
|
|---|
| 研究期間 (年度) |
2020-04-01 – 2024-03-31
|
| 研究課題ステータス |
完了 (2023年度)
|
| 配分額 *注記 |
3,770千円 (直接経費: 2,900千円、間接経費: 870千円)
2022年度: 390千円 (直接経費: 300千円、間接経費: 90千円)
2021年度: 1,300千円 (直接経費: 1,000千円、間接経費: 300千円)
2020年度: 2,080千円 (直接経費: 1,600千円、間接経費: 480千円)
|
|---|
| キーワード | Agents / Conversational AI / NLP / Deliberation / Interaction / Decision-making / Interdependence / Online Discussion / Online Debates / Agent Deliberation / Predictive Deliberation / Conversational Agents / Augmented Democracy / Mutual Information / Natural Language / Group Interaction / Similarity Metrics / Collaborative Editing / Time Series Analysis / Automatic Deliberation / Entropy Methods / Artificial Agent / Information Theory / Artificial Intelligence |
|---|
| 研究開始時の研究の概要 |
In this project, we propose to study the interactions between humans and artificial agents that maximize collective intelligence. Understanding the dynamics behind symbiotic interactions in online discussions is a viable way to foster intelligent deliberation and build smarter deliberative agents.
|
| 研究実績の概要 |
This final phase's achievement is applying previous metrics to practical cases of humans interacting with agents in a computational social study. The study was published in Nature's Scientific Reports and focuses on citizens participating in online debates, demonstrating that conversational agents can influence discussion dynamics, enhancing participation and reducing inhibition. The second key result builds on interaction metrics to propose a study published in the Journal of Social Network Analysis and Mining. I explored whether the structural complexity of online discussions can predict consensus readability without linguistic semantics. The findings indicate that entropy-based metrics effectively predict consensus readability based on the complexity of the discourse tree. These findings contribute to the symbiotic interactions between humans and intelligent deliberative agents in online discussion platforms.
|
