A Case Study on the Comparison of AI-facilitated Threaded Conversation versus Threaded Conversation
DOI:
https://doi.org/10.52731/liir.v004.179Keywords:
Threaded conversation, case study, facilitation, online forum, conversational AI, social experimentAbstract
In this paper, we present a process for collecting people's opinions by providing the public with and without an AI-facilitated online environment to post their views. Specifically, we targeted online communities on Facebook and directed them to D-Agree, an AI-powered online discussion forum. We want to explore the extent to which user participation in AI-assisted threaded conversation is successful by looking at the depth of threaded conversation while comparing threads not facilitated by AI facilitation. We deemed an AI facilitator to have successfully promoted the engagement if the discussion thread with an AI-facilitated thread had depth compared to discussion threads without an AI facilitator presence. Our analysis indicates that threaded conversation with conversational agent presence are successful. The collected insights can be used as a planning tool for developing conversational AI applications.
References
T. Ito, R. Hadfi, and S. Suzuki. An Agent that Facilitates Crowd Discussion. Group Decision and Negotiation, vol. 31, no. 3, pp. 621-647, 2022.
J. Haqbeen et al. In Solidarity with Ukraine through conversational AI via Facebook Ads: A case study of online discussion in 15 countries. In Proceedings of the 24th Annual International Conference on Digital Government Research (DG.O 2023), pp.
-641. 2023.
P. Howard et al. Opening Closed Regimes: What Was the Role of Social Media During the Arab Spring? Available SSRN: https://ssrn.com/abstract=2595096
J. Haqbeen, S. Sahab, T. Ito, P Rizzi. Using decision support system to enable crowd identify neighborhood issues and its solutions for policy makers: An online experiment at Kabul municipal level. Sustainability, vol. 13, no.10, p. 5453, 2021.
S. Sahab, J. Haqbeen, and T. Ito. Facilitating the Problems that lie within the Solutions using Conversational AI: A Case Study of Post-2021 Afghanistan. In Proceedings of the 24th Annual International Conference on Digital Government Research (DG.O2023), pp.13-24, 2023.
S. Sahab et al. What makes a Participative Tool Elicit more Sample Views? Discussion with Supportive Means for Mutual Benefit. In Proceedings of REAL CORP, 2021, pp.837-849.
S. Sahab et al. Different or Alike? Motivation to Participate and Social Influence in Online Discussions by Age and Gender. In Proceedings of REAL CORP, 2021, pp.281-289.
N. Tavanapour et al. Different or Alike? Supporting the Idea Generation Process in Citizen Participation-toward an Interactive System with a Conversational Agent as Facilitator. In Proceedings of the 27th European Conferece on Information Systems (ECIS), 2019.
R. Hadfi, J. Haqbeen, S. Sahab, T. Ito. Argumentative Conversational Agents for Online Discussions. Journal of Systems Science and Systems Engineering, vol. 30, no.1, pp. 450:464, 2021.
R. Hadfi, S. Okuhara J. Haqbeen, et al. Conversational agents enhace women’s contribution in online debates. Scientific Reports, vol. 30, no.1, pp. 14534, 2023.
S. Katz et al. When Should Dialogues in a Scaffolded Learning System. In Proceedings of theED-MEDIA, 2005, pp.2850-2855.
S. Palmer et al. Does the discussion help? The impact of a formally assessed online discussion on final student results. British Journal of Edcational Technology, vol. 39, no.5, pp. 847-858, 2008.
W. Kunz and H. W. Rittel. Issues as elements of information systems. Institute of Urban and Regional Development, University of California,vol. Working Paper No. 131, ed. Berkeley, California: 1970.
