2022 Fiscal Year Research-status 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, 特定助教 (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 / Interaction / Deliberation / NLP / Interdependence / Online Discussion / Decision-making |
|---|
| Outline of Annual Research Achievements |
The research resulted in the discovery and evaluation of various patterns of interaction in group discussions involving humans and conversational agents. The patterns where analyzed using a combination of techniques relying on time series analysis, information theory, natural language processing, and natural language generation. The results lead to an enhanced interpretation of the links between online debates and the underlying social dynamic. Moreover, the results helped in improving the implementation of artificial agents that interact with humans in various domains, including linguistic (conversational) and economic (negotiation) ones. These results come as an extension of the findings reported previously. The core findings were presented and published in various national and international conferences, workshops, and tutorials (AAMAS, PRICAI, KICSS, IEEE ICA, etc.). The key achievement of the research is laying out the foundation of platforms that allow humans to work effectively while interacting with conversational agents. This published form of "Augmented Democratic Deliberation" (AAMAS 2022) sets the future of online augmented democracies and addresses in a principled way key questions such as ethics, autonomy, and fairness. These notions will be investigated by the PI in other related research projects that exploit the present findings.
|
| 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 developed framework was validated both theoretically and technically in various settings that involve humans and AI. The research has clarified most of the questions that were initially posed. Currently, the most recent results and extensions of the project are under review in journals and are expected to be published.
|
| Strategy for Future Research Activity |
The plan is to finalize the publication of the most recent results applied to real-world settings (political debates). Such results are currently under review in journals. Overall, the results of the project helped refine the design and implementation of deliberative metrics that 1) enhance our understanding on online discourse, debates, and dynamics, and 2) improve the design principles of conversational agents. These points are crucial to current AI research and in investigating issues regarding safety, ethics, and respect of human agency.
|
| Causes of Carryover |
Some of the experimentations did not require hiring participants and collect data, instead data from existing datasets and previous experiments were used for the validation of the results. The remaining amount will therefore be used for some purchases as well as for the fees of publications of more recent results and extensions.
|
Research Products
(11 results)
