Description

Discussion support platforms are effective tools to moderate public debates and improve the quality of online discussions. Such platforms can be equipped with automated facilitation mechanisms that rely on autonomous and intelligent conversational agents. These agents can guide crowds into solving wicked social problems that cannot be handled by traditional decision-making approaches. This tutorial provides a comprehensive introduction into discussion support platforms, how they are developed using agent techniques, and how they can be deployed to solve societal problems.

In the first part of the tutorial, we will cover the literature of AI-enabled crowd discussion systems. We will start from the vision and literature on collective intelligence and dive into its agent applications. In the second part, we will provide a principled methodology for developing conversational agents in online discussions. The methodology combines agent-based development, Natural Language Processing/Generation, and formal argumentation theory. These different components will be integrated within one single framework that could be extended to existing communication platforms such as Slack or Teams. After showcasing a few development strategies, we will test the agents in experimental discussions. In the third part of the tutorial, we will cover real-world case studies from online experiments in Japan and Afghanistan. The proposed socio-technical methodology starts from particular social problems and explores the corresponding research questions, experimental designs, hypotheses, and how to address them using discussion support platforms. We will finally outline the importance of conducting social studies using autonomous and intelligent conversational agents.

Target Audience

The target audiences are students, researchers, academics, and AI practitioners interested in the fields of

• Multiagent Systems

• Collective Intelligence

• Crowd Decision Making

• Consensus Building

• Computational Social Science

• E-democracy

• AI for Social Good

• Natural Language Processing/Generation

• The development of Conversational Agents, Chatbots, and Socialbots

Prerequisites

For the first part, a general knowledge about AI is required. For the second part, it is preferable that the participants have some basic knowledge about agent-based development, Python programming, and Natural Language Processing. For the third part, there is no strict requirement. Basic knowledge of social sciences and experimental design will be an advantage.

Date

19:00 – 22:00, May 10, Auckland Time

3:00 – 6:00, May 10, New York Time

9:00 – 12:00, May 10, Paris Time

12:30 – 15:30, May 10, Kolkata Time

15:00 – 18:00, May 10, Beijing Time

16:00 – 19:00, May 10, Japan Time

Duration

3 hours

Outline

1. Recent Advances on Crowd-based Discussion Platforms

Takayuki Ito (Kyoto University): 60 min

2. Developing Conversational Agents for Argumentative Discussions

Rafik Hadfi (Kyoto University) : 60 min

3. Promoting Deliberative Democracy with AI-based Facilitation: Case Studies from Afghanistan and Japan

Sofia Sahab (Kyoto University): 60 min

4. Q and A, Wrap-up: 30 min

Tutorial Material

The slides of the tutorial can be found here.

Presenters

Rafik Hadfi is a Research Assistant Professor in the Department of Social Informatics at Kyoto University. He received his PhD from Nagoya Institute of Technology in 2015 and has worked in Japan and Australia before joining Kyoto University in 2020. His research interests lie in the design, development and application of multiagent systems for social simulation and collective decision making. He is currently using conversational AI to study deliberation, polarization, and fairness in social networks. Rafik served as Program Committee member of leading AI conferences such as IJCAI, AAMAS, SNPD, IEEE ICA and reviewer for Group Decision and Negotiation; Artificial Intelligence Review; Neural Computation; Advanced Computational Intelligence and Intelligent Informatics; and Networked and Distributed Computing. Rafik has been the publication chair, workshops chair, tutorials chair, volunteers chair, and web chair for international AI conferences such as IJCAI, PRICAI, PRIMA and IEEE ICA. In 2022, he will serve as the Program Chair of IEEE ICA. Rafik received the annual conference award from Japan Society for Artificial Intelligence (2020), IBM Award of Scientific Excellence (2020), Best Paper Award from Information Processing Society of Japan (2016), IEEE Young researcher Award (2014), and AAAI Student Scholarship Award (2014).

Takayuki Ito is Professor of Kyoto University. He received the B.E., M.E, and Doctor of Engineering from the Nagoya Institute of Technology in 1995, 1997, and 2000, respectively. From 1999 to 2001, he was a research fellow of the Japan Society for the Promotion of Science (JSPS). From 2000 to 2001, he was a visiting researcher at USC/ISI (University of Southern California/Information Sciences Institute). From April 2001 to March 2003, he was an associate professor of Japan Advanced Institute of Science and Technology (JAIST). From April 2004 to March 2013, he was an associate professor of Nagoya Institute of Technology. From April 2014 to September 2020, he was a professor of Nagoya Institute of Technology. From October 2020, he is a professor of Kyoto University. From 2005 to 2006, he is a visiting researcher at Division of Engineering and Applied Science, Harvard University and a visiting researcher at the Center for Coordination Science, MIT Sloan School of Management. From 2008 to 2010, he was a visiting researcher at the Center for Collective Intelligence, MIT Sloan School of Management, again. From 2017 to 2018, he is a invited researcher of Artificial Intelligence Center of AIST, JAPAN. From March 5, 2019, he is the CTO of AgreeBit, inc. He is a board member of IFAAMAS, Executive Committee Member of IEEE Computer Society Technical Committee on Intelligent Informatics, the PC-chair of AAMAS2013, PRIMA2009, the Local Arrangements Chair of IJCAI-PRICAI2020, General-Chair of PRIMA2014, and was a SPC/PC member in many top-level conferences (IJCAI, AAMAS, ECAI, AAAI, etc). He received the JSAI (Japan Society for Artificial Intelligence) Contribution Award, the JSAI Achievement Award, the JSPS Prize, 2014, the Prize for Science and Technology (Research Category), The Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science, and Technology, 2013, the Young Scientists' Prize, The Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science, and Technology, 2007, the Nagao Special Research Award of the Information Processing Society of Japan, 2007, the Best Paper Award of AAMAS2006, the 2005 Best Paper Award from Japan Society for Software Science and Technology, the Best Paper Award in the 66th annual conference of 66th Information Processing Society of Japan, and the Super Creator Award of 2004 IPA Exploratory Software Creation Projects. He is Principle Investigator of the Japan Cabinet Funding Program for Next Generation World-Leading Researchers (NEXT Program). Further, he has several companies, which are handling web-based systems and enterprise distributed systems. His main research interests include multi-agent systems, intelligent agents, group decision support systems, agent-mediated electronic commerce, and software engineering on offshoring.

Sofia Sahab received the B.S. degree in architectural engineering from Kabul University in 2009, and M.E., and Doctor of Engineering Degrees in urban planning from Nagoya Institute of Technology, Japan, in 2014 and 2017, respectively. She is currently a specially appointed researcher at Kyoto University. She previously worked as assistant professor with Nagoya Institute of Technology, Japan, and Kabul University, Afghanistan. Her current research interests include participatory urban planning, smart cities and communities, and applying artificial intelligence to civic technologies. She has published research articles in journals, such as Journal of Simulation and Gaming (SAGE Publications) and Journal of Architecture and Planning (Transections of Architectural Institute of Japan).

References

Please contact Rafik (rafik.hadfi [at] i.kyoto-u.ac.jp) if you have any questions or feedback.