Abstract
An important subdomain in research on Human-Artificial Intelligence interaction is Explainable AI (XAI). XAI attempts to improve human understanding and trust in machine intelligence and automation by providing users with visualizations and other information that explain decisions, actions, and plans. XAI approaches have primarily used algorithmic approaches designed to generate explanations automatically, but an alternate route that may augment these systems is to take advantage of the fact that user understanding of AI systems often develops through self-explanation [1]. Users engage in this to piece together different sources of information and develop a clearer understanding, but these self-explanations are often lost if not shared with others. We demonstrate how this ‘Self-Explanation’ can be shared collaboratively via a system we call collaborative XAI (CXAI), akin to a Social Q&A platform [2] such as StackExchange. We will describe the system and evaluate how it supports various kinds of explanations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Mueller, S.T., et al.: Principles of explanation in human-AI systems. ArXiv Prepr. ArXiv210204972 (2021)
Oh, S.: Social Q&A. In: Brusilovsky, P., He, D. (eds.) Social Information Access. LNCS, vol. 10100, pp. 75–107. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-90092-6_3
Klein, G.A.: Naturalistic decision making. Hum. Factors 50(3), 456–460 (2008)
Chi, M.T., Wylie, R.: The ICAP framework: linking cognitive engagement to active learning outcomes. Educ. Psychol. 49(4), 219–243 (2014)
Dillenbourg, P.: What do you mean by collaborative learning? (1999)
Webb, N.M.: Group composition, group interaction, and achievement in cooperative small groups. J. Educ. Psychol. 74(4), 475 (1982)
Vygotsky, L.S.: Mind in Society: The Development of Higher Psychological Processes. Harvard University Press (1980)
Gokhale, A.A.: Collaborative learning enhances critical thinking. J. Technol. Educ. 7(1) (1995)
Johnson, D.W.: Effectiveness of role reversal: actor or listener. Psychol. Rep. 28(1), 275–282 (1971)
Peterson, P.L., Swing, S.R.: Students’ cognitions as mediators of the effectiveness of small-group learning. J. Educ. Psychol. 77(3), 299 (1985)
Koschmann, T.D.: CSCL, Theory and Practice of An Emerging Paradigm. Routledge (1996)
Scardamalia, M., Bereiter, C.: Computer support for knowledge-building communities. J. Learn. Sci. 3(3), 265–283 (1994)
Liaw, S.-S.: Considerations for developing constructivist web-based learning. Int. J. Instr. Media 31, 309–319 (2004)
Liaw, S.-S., Chen, G.-D., Huang, H.-M.: Users’ attitudes toward Web-based collaborative learning systems for knowledge management. Comput. Educ. 50(3), 950–961 (2008). https://doi.org/10.1016/j.compedu.2006.09.007
Slotta, J.D., Najafi, H.: Supporting collaborative knowledge construction with web 2.0 technologies. In: Mouza, C., Lavigne, N. (eds.) Emerging Technologies for the Classroom. Explorations in the Learning Sciences, Instructional Systems and Performance Technologies, pp. 93–112. Springer, New York (2013). https://doi.org/10.1007/978-1-4614-4696-5_7
Paul, S.A., Morris, M.R.: CoSense: enhancing sensemaking for collaborative web search. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 1771–1780 (2009)
Graesser, A.C., Baggett, W., Williams, K.: Question-driven explanatory reasoning. Appl. Cogn. Psychol. 10(7), 17–31 (1996)
Mueller, S.T., Hoffman, R.R., Clancey, W., Emrey, A., Klein, G.: Explanation in human-AI systems: a literature meta-review, synopsis of key ideas and publications, and bibliography for explainable AI, ArXiv Prepr. ArXiv190201876 (2019)
Care, E., Griffin, P., Scoular, C., Awwal, N., Zoanetti, N.: Collaborative problem solving tasks. In: Griffin, P., Care, E. (eds.) Assessment and Teaching of 21st Century Skills. Educational Assessment in an Information Age, pp. 85–104. Springer, Dordrecht (2015). https://doi.org/10.1007/978-94-017-9395-7_4
Shah, C., Oh, S., Oh, J.S.: Research agenda for social Q&A. Libr. Inf. Sci. Res. 31(4), 205–209 (2009)
Jin, J., Li, Y., Zhong, X., Zhai, L.: Why users contribute knowledge to online communities: an empirical study of an online social Q&A community. Inf. Manage. 52(7), 840–849 (2015)
Nam, K.K., Ackerman, M.S., Adamic, L.A.: Questions in, knowledge in? A study of Naver’s question answering community. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 779–788 (2009)
Zhou, J., Wang, S., Bezemer, C.-P., Hassan, A.E.: Bounties on technical Q&A sites: a case study of stack overflow bounties. Empir. Softw. Eng. 25(1), 139–177 (2020)
Lim, B.Y., Dey, A.K.: Assessing demand for intelligibility in context-aware applications. In: Proceedings of the 11th International Conference on Ubiquitous Computing, pp. 195–204 (2009)
Acknowledgment and Disclaimer
This research was developed with funding from the Defense Advanced Research Projects Agency (DARPA). This material is approved for public release. Distribution is unlimited. This material is based on research sponsored by the AirForce Research Lab (AFRL) under agreement number FA8650-17-2-7711. Approved for public release, Distribution Unlimited.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Mamun, T.I., Hoffman, R.R., Mueller, S.T. (2021). Collaborative Explainable AI: A Non-algorithmic Approach to Generating Explanations of AI. In: Stephanidis, C., Antona, M., Ntoa, S. (eds) HCI International 2021 - Late Breaking Posters. HCII 2021. Communications in Computer and Information Science, vol 1498. Springer, Cham. https://doi.org/10.1007/978-3-030-90176-9_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-90176-9_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-90175-2
Online ISBN: 978-3-030-90176-9
eBook Packages: Computer ScienceComputer Science (R0)