Argumentative Conversational Agents for Online Discussions

Abstract

Artificial Intelligence is revolutionising our communication practices and the ways in which we interact with each other. This revolution does not only impact how we communicate, but it affects the nature of the partners with whom we communicate. Online discussion platforms now allow humans to communicate with artificial agents in the form of socialbots. Such agents have the potential to moderate online discussions and even manipulate and alter public opinions. In this paper, we propose to study this phenomenon using a constructed large-scale agent platform. At the heart of the platform lies an artificial agent that can moderate online discussions using argumentative messages. We investigate the influence of the agent on the evolution of an online debate involving human participants. The agent will dynamically react to their messages by moderating, supporting, or attacking their stances. We conducted two experiments to evaluate the platform while looking at the effects of the conversational agent. The first experiment is a large-scale discussion with 1076 citizens from Afghanistan discussing urban policy-making in the city of Kabul. The goal of the experiment was to increase the citizen involvement in implementing Sustainable Development Goals. The second experiment is a small-scale debate between a group of 16 students about globalisation and taxation in Myanmar. In the first experiment, we found that the agent improved the responsiveness of the participants and increased the number of identified ideas and issues. In the second experiment, we found that the agent polarised the debate by reinforcing the initial stances of the participant.

Keywords

Artificial intelligence / conversational agents / natural language processing / online discussion / computational social science

References

[1] Al-ZubaideH, IssaAAInternational Symposium on Innovations in Information and Communications Technology, 2011

[2] AmgoudL, ParsonsS, MaudetNEuropean Conference on Artificial Intelligence (ECAI2000), 2000

[3] AmgoudL, CayrolC, Lagasquie-SchiexMC, LivetP. On bipolarity in argumentation frameworks. International Journal of Intelligent Systems, 2008, 23(10): 1062-1093

[4] BailCA, ArgyleLP, BrownTW, BumpusJP, ChenH, HunzakerMF, LeeJ, MannM, MerhoutF, VolfovskyA. Exposure to opposing views on social media can increase political polarization. Proceedings of the National Academy of Sciences, 2018, 115(37): 9216-9221

[5] BaroniP, GiacominM. On principle-based evaluation of extension-based argumentation semantics. Artificial Intelligence, 2007, 171(10–15): 675-700

[6] BistarelliS, RossiF, SantiniF2017 IEEE 29th International Conference on Tools with Artificial Intelligence, 2017

[7] BojanowskiP, GraveE, JoulinA, MikolovT. Enriching word vectors with subword information. Transactions of:the Association for Computational Linguistics, 2017, 5: 135-146

[8] CayrolC, Lagasquie-SchiexMCConference on Symbolic and Quantitative Approaches to Reasoning and Uncertainty, 2005

[9] ChenH, LiuX, YinD, TangJ. A survey on dialogue systems: Recent advances and new frontiers. Sigkdd Explorations Newsletter, 2017, 19(2): 25-35

[10] Csaky R (2019). Deep learningbased chatbot models. arXiv preprint arXiv:190808835.

[11] DungPM. On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games. Artificial Intelligence, 1995, 77(2): 321-357

[12] Ferrara E (2017). Disinformation and social bot operations in the run up to the 2017 French presidential election. arXiv preprint arXiv:170700086.

[13] FoxJ, ParsonsSProceedings of the AAAI Spring Symposium on Qualitative Preferences in Deliberation and Practical Reasoning, 1997

[14] GravesA, SchmidhuberJ. Framewise phoneme classification with bidirectional lstm and other neural network architectures. Neural Networks, 2005, 18(5–6): 602-610

[15] HaqbeenJ, ItoT, HadfiR, NishidaT, SahabZ, SahabS, RoghmalS, AmiryarRProceeding of the 8th ACM Collective Intelligence Conference, 2020

[16] HaqbeenJ, ItoT, SahabS, HadfiR, OkuharaS, SabaN, HofianiM, BaregzaiUAI for Social Good Workshop, 2020

[17] HussainS, SianakiOA, AbabnehNWorkshops of the International ConferenceonAdvanced Information Networking and Applications, 2019

[18] IandoliL, KleinM, ZolloGMIT Sloan Research Paper, 2007

[19] ItoT, ImiY, ItoT, HideshimaECollective Intelligence, 2014

[20] ItoT, ImiY, SatoM, ItoT, HideshimaECollective Intelligence, 2015

[21] ItoT, ShibataD, SuzukiS, YamaguchiN, NishidaT, HiraishiK, YoshinoK7th ACM Collective Intelligence, 2019

[22] KeuschniggM, LovsjöN, HedströmP. Analytical sociology and computational social science. Journal of Computational Social Science, 2018, 1(1): 3-14

[23] KolkoJWicked Problems: Problems Worth Solving, 2012

[24] Kunz W, Rittel HW (1970). Issues as elements of information systems, vol 131. CiteSeer.

[25] MaloneTWSuperminds: The surprising power of people and computers thinking together, 2018

[26] MaloneTW, KleinM. Harnessing collective intelligence to address global climate change. Innovations: Technology, Governance, Globalization, 2007, 2(3): 15-26

[27] NofalS, AtkinsonK, DunnePEThe 11th International Conference on Knowledge Engineering and Ontology Development, 2019

[28] NofalS, AtkinsonK, DunnePE, HababehIProceedings of the 21st International Conference on Enterprise Information Systems, 2019

[29] Nuez Ezquerra A (2018). Implementing chatbots using neural machine translation techniques. B.S. thesis, Universitat Politècnica de Catalunya.

[30] OzerM, YildirimMY, DavulcuHProceedings of ACM Conference (Conference’17), 2019

[31] SavagetP, ChiariniT, EvansS. Empowering political participation through artificial intelligence. Science and Public Policy, 2019, 46(3): 369-380

[32] ShaoC, CiampagliaGL, VarolO, YangKC, FlamminiA, MenczerF. The spread of low-credibility content by social bots. Nature Communications, 2018, 9(1): 1-9

[33] StellaM, FerraraE, De DomenicoM. Bots increase exposure to negative and inflammatory content in online social systems. Proceedings of the National Academy of Sciences, 2018, 115(49): 12435-12440

[34] SunsteinCREcho Chambers: Bush v. Gore, Impeachment, and Beyond, 2001, Princeton, NJ, Princeton University Press

[35] SuzukiS, YamaguchiN, NishidaT, MoustafaA, ShibataD, YoshinoK, HiraishiK, ItoTAnnual Conference of the Japanese Society for Artificial Intelligence, 2019

[36] VarolO, FerraraE, DavisCA, MenczerF, FlamminiAEleventh International AAAI Conference on Web and Social Media, 2017

[37] WallaceRSParsing the Turing Test, 2009

[38] WeizenbaumJ. Eliza — A computer program for the study of natural language communication between man and machine. Communications of the ACM, 1966, 9(1): 36-45

[39] WittigM, WittigA, WhaleyBAmazon Web Services in Action, 2016

[40] WoolleyAW, ChabrisCF, PentlandA, HashmiN, MaloneTW. Evidence for a collective intelligence factor in the performance of human groups. Science, 2010, 330(6004): 686-688

[41] YanZ, DuanN, ChenP, ZhouM, ZhouJ, LiZThirty-First AAAI Conference on Artificial Intelligence, 2017

RIGHTS & PERMISSIONS

Systems Engineering Society of China and Springer-Verlag GmbH Germany