Abstract
Artificial Intelligence (AI) models operate as black boxes where most parts of the system are opaque to users. This reduces the user’s trust in the system. Although the Human-Computer Interaction (HCI) community has proposed design practices to improve transparency, work that provides a mapping of these practices and interactive elements that influence AI transparency is still lacking. In this paper, we conduct an in-depth literature survey to identify elements that influence transparency in the field of HCI. Research has shown that transparency allows users to have a better sense of the accuracy, fairness, and privacy of a system. In this context, much research has been conducted on providing explanations for the decisions made by AI systems. Researchers have also studied the development of interactive interfaces that allow user interaction to improve the explanatory capability of systems. This literature review provides key insights about transparency and what the research community thinks about it. Based on the insights gained we gather that a simplified explanation of the AI system is key. We conclude the paper with our proposed idea of representing an AI system, which is an amalgamation of the AI Model (algorithms), data (input and output, including outcomes), and the user interface, as visual interpretations (e.g. Venn diagrams) can aid in understanding AI systems better and potentially making them more transparent.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anik, A.I., Bunt, A.: Data-centric explanations: explaining training data of machine learning systems to promote transparency. In: Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems (2021)
Bertino, E., Merrill, S., Nesen, A.: A multidimensional approach. Computer, Redefining data transparency (2019)
Burrell, J.: How the machine ‘thinks’: Understanding opacity in machine learning algorithms. Big Data Soc. 3(1), 2053951715622512 (2016)
Cheng, H.F., et al.: Strategies to help non-expert stakeholders, Explaining decision-making algorithms through UI (2019)
Chromik, M., Eiband, M., Völkel, S.T., Buschek, D.: Dark patterns of explainability, transparency, and user control for intelligent systems. In: IUI Workshops (2019)
Clinciu, M., Hastie, H.: A survey of explainable AI terminology. In: Proceedings of the 1st Workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence, pp. 8–13. Association for Computational Linguistics (2019)
Cramer, H., et al.: The effects of transparency on trust and acceptance in interaction with a content-based art recommender. User Model. User-Adapt. Interact. 18, 455–496 (2008)
Diakopoulos, N.A.: Accountability in algorithmic decision making. Commun. ACM 59(2), 56–62 (2016)
Fallon, C.K., Blaha, L.M.: Improving automation transparency: addressing some of machine learning’s unique challenges (2018)
Ferrario, A., Loi, M., Viganò, E.: In AI we trust incrementally: a multi-layer model of trust to analyze human-artificial intelligence interactions. Philos. Technol. 33(3), 523–539 (2019). https://doi.org/10.1007/s13347-019-00378-3
Ozmen Garibay, O., et al.: Six human-centered artificial intelligence grand challenges. Int. J. Hum.-Comput. Interact. 39(3), 391–437 (2023)
Gilpin, L., Paley, A., Alam, M., Spurlock, S., Hammond, K.: Explanation is not a technical term: the problem of ambiguity in xai (2022)
Gilpin, L.H., Bau, D., Yuan, B.Z., Bajwa, A., Specter, M., Kagal, L.: Explaining explanations: an overview of interpretability of machine learning. In: 2018 IEEE 5th International Conference on Data Science and Advanced Analytics (DSAA) (2018)
Glass, A., McGuinness, D.L., Wolverton, M.: Toward establishing trust in adaptive agents. In: Proceedings of the 13th International Conference on Intelligent User Interfaces (2008)
Gregor, S., Benbasat, I.: Explanations from intelligent systems: theoretical foundations and implications for practice. MIS Q. 23(4), 497–530 (1999)
Hollanek, T.: Ai transparency: a matter of reconciling design with critique. AI & Soc. (2020). https://doi.org/10.1007/s00146-020-01110-y
Höök, K.: Steps to take before intelligent user interfaces become real. Interact. Comput. 12(4), 409–426 (2000)
Kirsch, A.: Explain to whom? putting the user in the center of explainable AI. In: Proceedings of the First International Workshop on Comprehensibility and Explanation in AI and ML (2017)
Kulesza, T., Stumpf, S., Burnett, M., Yang, S., Kwan, I., Wong, W.K.: Too much, too little, or just right? ways explanations impact end users’ mental models. In: 2013 IEEE Symposium on Visual Languages and Human Centric Computing (2013)
Lim, B.Y., Dey, A.K., Avrahami, D.: Why and why not explanations improve the intelligibility of context-aware intelligent systems. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (2009)
Liu, B.: In AiIwe trust? effects of agency locus and transparency on uncertainty reduction in human-AI interaction. J. Comput.-Med. Commun. 26(6), 384–402 (2021)
Lopes, P., Silva, E., Braga, C., Oliveira, T., Rosado, L.: A review of human and computer-centred methods. Appl. Sci. Xai Syst. Eval. 12(19), 9423 (2022)
Miller, C.: Delegation and transparency: Coordinating interactions so information exchange is no surprise, June 2014
Miller, T.: Explanation in artificial intelligence: Insights from the social sciences. Artif. Intell. 267, 1–38 (2019)
Mittelstadt, B., Russell, C., Wachter, S.: Explaining explanations in AI. In: Proceedings of the Conference on Fairness, Accountability, and Transparency (2019)
Montavon, G., Lapuschkin, S., Binder, A., Samek, W., Müller, K.-R.: Explaining nonlinear classification decisions with deep taylor decomposition. Pattern Recogn. 65, 211–222 (2017)
Montavon, G., Samek, W., Müller, K.R.: Methods for interpreting and understanding deep neural networks. Digit. Sig. Process. 73, 1–15 (2018)
Nielsen, J.: Enhancing the explanatory power of usability heuristics. In: Proceedings of the SIGCHI conference on Human Factors in Computing Systems, pp. 152–158 (1994)
Donald, A.: Norman. Basic Books Inc, The Design of Everyday Things (2002)
Ribeiro, M.T., Singh, S. and Guestrin, C.: Why should i trust you?: explaining the predictions of any classifier (2016)
Rubin, V.: Ai opaqueness: what makes AI systems more transparent? In: Proceedings of the Annual Conference of CAIS/Actes du congrès annuel de l’ACSI, November 2020
Springer, A., Whittaker, S.: Progressive disclosure: when, why, and how do users want algorithmic transparency information? ACM Trans. Interact. Intell. Syst. 10(4), 1–32 (2020)
Tintarev, N., Masthoff, J.: Designing and evaluating explanations for recommender systems (2011)
Tomsett, R., Braines, D., Harborne, D., Preece, A., Chakraborty, S.: Supriyo: interpretable to whom? A role-based model for analyzing interpretable machine learning systems, CoRR (2018)
van Nuenen, T., Ferrer, X., Such, J.M., Cote, M.: Transparency for whom? assessing discriminatory artificial intelligence. Computer 53(11), 36–44 (2020)
Weller, A.: Transparency: motivations and challenges (2019)
Lipton Zachary, C.: The mythos of model interpretability. Queue 16(3), 31–57 (2018)
Zerilli, J., Knott, A., Maclaurin, J., Gavaghan, C.: Transparency in algorithmic and human decision-making: is there a double standard? Philos. Technol. 32(4), 661–683 (2018). https://doi.org/10.1007/s13347-018-0330-6
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Muralidhar, D., Belloum, R., de Oliveira, K.M., Ashok, A. (2023). Elements that Influence Transparency in Artificial Intelligent Systems - A Survey. In: Abdelnour Nocera, J., Kristín Lárusdóttir, M., Petrie, H., Piccinno, A., Winckler, M. (eds) Human-Computer Interaction – INTERACT 2023. INTERACT 2023. Lecture Notes in Computer Science, vol 14142. Springer, Cham. https://doi.org/10.1007/978-3-031-42280-5_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-42280-5_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42279-9
Online ISBN: 978-3-031-42280-5
eBook Packages: Computer ScienceComputer Science (R0)