2023 Fiscal Year Annual Research Report
Measuring Group Interaction in Online Discussions and Application to Autonomous Agent Deliberation
| Project/Area Number |
20K11936
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
Rafik Hadfi 京都大学, 情報学研究科, 特定准教授 (30867495)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
伊藤 孝行 名古屋工業大学, 工学(系)研究科(研究院), 教授 (50333555)
|
|---|
| Project Period (FY) |
2020-04-01 – 2024-03-31
|
| Keywords | Agents / Conversational AI / NLP / Deliberation / Interaction / Decision-making / Interdependence / Online Discussion |
|---|
| Outline of Annual Research Achievements |
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.
|
