Abstract
The present study investigates the effects of prototypical visualization approaches aimed at increasing the explainability of machine learning systems in regard to perceived trustworthiness and observability. As the amount of processes automated by artificial intelligence (AI) increases, so does the need to investigate users’ perception. Previous research on explainable AI (XAI) tends to focus on technological optimization. The limited amount of empirical user research leaves key questions unanswered, such as which XAI designs actually improve perceived trustworthiness and observability. We assessed three different visual explanation approaches, consisting of either only a table with classification scores used for classification, or, additionally, one of two different backtraced visual explanations. In a within-subjects design with N = 83 we examined the effects on trust and observability in an online experiment. While observability benefitted from visual explanations, information-rich explanations also led to decreased trust. Explanations can support human-AI interaction, but differentiated effects on trust and observability have to be expected. The suitability of different explanatory approaches for individual AI applications should be further examined to ensure a high level of trust and observability in e.g. automated image processing.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access. 6, 52138–52160 (2018). https://doi.org/10.1109/ACCESS.2018.2870052
Weld, D.S., Bansal, G.: The Challenge of Crafting Intelligible Intelligence. ArXiv180304263 Cs. (2018)
Ancona, M., Ceolini, E., Öztireli, C., Gross, M.: Towards better understanding of gradient-based attribution methods for Deep Neural Networks. ArXiv171106104 Cs Stat. (2017)
Lee, J.D., See, K.A.: Trust in automation: designing for appropriate reliance. Hum. Factors 46, 50–80 (2004)
Lee, J., Moray, N.: Trust, control strategies and allocation of function in human-machine systems. Ergonomics 35, 1243–1270 (1992). https://doi.org/10.1080/00140139208967392
Muir, B.M., Moray, N.: Trust in automation. Part II experimental studies of trust and human intervention in a process control simulation. Ergonomics. 39, 429–460 (1996). https://doi.org/10.1080/00140139608964474
Nushi, B., Kamar, E., Horvitz, E.: Towards Accountable AI: Hybrid Human-Machine Analyses for Characterizing System Failure. ArXiv180907424 Cs Stat. (2018)
Lim, B.Y., Dey, A.K.: Assessing demand for intelligibility in context-aware applications. In: Proceedings of the 11th international conference on Ubiquitous computing (Ubicomp 2009). p. 195. ACM Press, Orlando (2009). https://doi.org/10.1145/1620545.1620576
Montavon, G., Samek, W., Müller, K.-R.: Methods for interpreting and understanding deep neural networks. Digit. Signal Process. 73, 1–15 (2018). https://doi.org/10.1016/j.dsp.2017.10.011
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why Should I Trust You?”: Explaining the Predictions of Any Classifier. ArXiv160204938 Cs Stat. (2016)
Kruger, J., Wirtz, D., Van Boven, L., Altermatt, T.W.: The effort heuristic. J. Exp. Soc. Psychol. 40, 91–98 (2004). https://doi.org/10.1016/S0022-1031(03)00065-9
Abdul, A., Vermeulen, J., Wang, D., Lim, B.Y., Kankanhalli, M.: Trends and trajectories for explainable, accountable and intelligible systems: an HCI research agenda. In: Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI 2018), pp. 1–18. ACM Press, Montreal QC (2018). https://doi.org/10.1145/3173574.3174156
Amershi, S., et al.: Guidelines for human-AI interaction. In: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems (CHI 2019), pp. 1–13. ACM Press, Glasgow (2019). https://doi.org/10.1145/3290605.3300233
Miller, T.: Explanation in Artificial Intelligence: Insights from the Social Sciences. ArXiv170607269 Cs. (2017)
Lapuschkin, S., Binder, A., Montavon, G., Müller, K.-R., Samek, W.: The LRP toolbox for artificial neural networks. J. Mach. Learn. Res. 17(1), 3938–3942 (2016)
Hoffman, R.R., Mueller, S.T., Klein, G., Litman, J.: Metrics for explainable AI: Challenges and prospects. ArXiv Prepr. ArXiv181204608. (2018)
Ras, G., van Gerven, M., Haselager, P.: Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges. ArXiv180307517 Cs Stat. (2018)
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 618–626. IEEE, Venice (2017). https://doi.org/10.1109/ICCV.2017.74
Samek, W., Wiegand, T., Müller, K.-R.: Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models. ArXiv170808296 Cs Stat. (2017)
Binder, A., Bach, S., Montavon, G., Müller, K.-R., Samek, W.: Layer-Wise Relevance Propagation for Deep Neural Network Architectures. Information Science and Applications (ICISA) 2016. LNEE, vol. 376, pp. 913–922. Springer, Singapore (2016). https://doi.org/10.1007/978-981-10-0557-2_87
Timmermans, D.: The impact of task complexity on information use in multi-attribute decision making. J. Behav. Decis. Mak. 6, 95–111 (1993). https://doi.org/10.1002/bdm.3960060203
Furner, C.P., Zinko, R.A.: The influence of information overload on the development of trust and purchase intention based on online product reviews in a mobile vs. web environment: an empirical investigation. Electron. Mark. 27, 211–224 (2017). https://doi.org/10.1007/s12525-016-0233-2
Roese, N.J., Morrison, M.: The psychology of counterfactual thinking. Hist. Soc. Res. Sozialforschung 16–26 (2009)
Sokol, K., Flach, P.: Glass-Box: explaining AI decisions with counterfactual statements through conversation with a voice-enabled virtual assistant. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence Organization, Stockholm, Sweden, pp. 5868–5870 (2018). https://doi.org/10.24963/ijcai.2018/865
Kulesza, T., Stumpf, S., Burnett, M., Kwan, I.: Tell me more? The effects of mental model soundness on personalizing an intelligent agent. In: Proceedings of the 2012 ACM annual conference on Human Factors in Computing Systems (CHI 2012), p. 1. ACM Press, Austin (2012). https://doi.org/10.1145/2207676.2207678
Goyal, Y., Wu, Z., Ernst, J., Batra, D., Parikh, D., Lee, S.: Counterfactual Visual Explanations. ArXiv190407451 Cs Stat. (2019)
Bigras, E., et al.: In AI we trust: characteristics influencing assortment planners’ perceptions of AI based recommendation agents. In: Nah, F.F.-H., Xiao, B.S. (eds.) HCIBGO 2018. LNCS, vol. 10923, pp. 3–16. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91716-0_1
Breuer, C., Hüffmeier, J., Hibben, F., Hertel, G.: Trust in teams: a taxonomy of perceived trustworthiness factors and risk-taking behaviors in face-to-face and virtual teams. Hum. Relat. (2019). https://doi.org/10.1177/0018726718818721
Zanker, M.: The influence of knowledgeable explanations on users’ perception of a recommender system. In: Proceedings of the sixth ACM conference on Recommender systems (RecSys 2012), p. 269. ACM Press, Dublin (2012). https://doi.org/10.1145/2365952.2366011
Springer, A., Whittaker, S.: “I had a solid theory before but it’s falling apart”: polarizing effects of algorithmic transparency. arXiv preprint arXiv:1811.02163 (2018)
Hengstler, M., Enkel, E., Duelli, S.: Applied artificial intelligence and trust—The case of autonomous vehicles and medical assistance devices. Technol. Forecast. Soc. Change. 105, 105–120 (2016). https://doi.org/10.1016/j.techfore.2015.12.014
Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., Elhadad, N.: Intelligible models for healthcare: predicting pneumonia risk and hospital 30-day readmission. In: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2015), pp. 1721–1730. ACM Press, Sydney (2015). https://doi.org/10.1145/2783258.2788613
Krause, J., Perer, A., Bertini, E.: A user study on the effect of aggregating explanations for interpreting machine learning models. In: ACM KDD Workshop on Interactive Data Exploration and Analytics (2018)
Kalman, R.E.: A new approach to linear filtering and prediction problems. J. Basic Eng. 82, 35–45 (1960)
Billings, C.E.: Human-centered aviation automation: principles and guidelines (1996)
Johnson, M., Bradshaw, J.M., Feltovich, P.J.: Tomorrow’s human–machine design tools: from levels of automation to interdependencies. J. Cogn. Eng. Decis. Mak. 12, 77–82 (2018). https://doi.org/10.1177/1555343417736462
Rovira, E., McGarry, K., Parasuraman, R.: Effects of imperfect automation on decision making in a simulated command and control task. Hum. Factors J. Hum. Factors Ergon. Soc. 49, 76–87 (2007). https://doi.org/10.1518/001872007779598082
Franke, T., Attig, C., Wessel, D.: A personal resource for technology interaction development and validation of the affinity for technology interaction (ATI) Scale. Int. J. Hum.-Comput. Inter. 35, 456–467 (2019). https://doi.org/10.1080/10447318.2018.1456150
Deng, L.: The MNIST database of handwritten digit images for machine learning research [best of the web]. IEEE Signal Process. Mag. 29, 141–142 (2012). https://doi.org/10.1109/MSP.2012.2211477
Franke, T., Trantow, M., Günther, M., Krems, J.F., Zott, V., Keinath, A.: Advancing electric vehicle range displays for enhanced user experience: the relevance of trust and adaptability. In: Proceedings of the 7th International Conference on Automotive User Interfaces and Interactive Vehicular Applications (AutomotiveUI 2015). pp. 249–256. ACM Press, Nottingham (2015). https://doi.org/10.1145/2799250.2799283
Jian, J.-Y., Bisantz, A.M., Drury, C.G.: Foundations for an empirically determined scale of trust in automated systems. Int. J. Cogn. Ergon. 4, 53–71 (2000). https://doi.org/10.1207/S15327566IJCE0401_04
Mauchly, J.W.: Significance test for sphericity of a normal n-Variate distribution. Ann. Math. Stat. 11, 204–209 (1940). https://doi.org/10.1214/aoms/1177731915
Greenhouse, S.W., Geisser, S.: On methods in the analysis of profile data. Psychometrika 24, 95–112 (1959). https://doi.org/10.1007/BF02289823
Holm, S.: A simple sequentially rejective multiple test procedure. Scand. J. Stat. 6, 65–70 (1979)
Cohen, J.: A power primer. Psychol. Bull. 112, 155–159 (1992). https://doi.org/10.1037/0033-2909.112.1.155
Dunlap, W.P., Cortina, J.M., Vaslow, J.B., Burke, M.J.: Meta-analysis of experiments with matched groups or repeated measures designs. Psychol. Methods 1(2), 170 (1996)
Kizilcec, R.F.: How much information? Effects of transparency on trust in an algorithmic interface. In: Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems (CHI 2016). pp. 2390–2395. ACM Press, Santa Clara (2016). https://doi.org/10.1145/2858036.2858402
Biros, D.P., Fields, G., Gunsch, G.: The effect of external safeguards on human-information system trust in an information warfare environment. In: Proceedings of the 36th Annual Hawaii International Conference on System Sciences 2003, p. 10. IEEE, Big Island (2003). https://doi.org/10.1109/HICSS.2003.1173894
Christoffersen, K., Woods, D.: How to make automated systems team players. Adv. Hum. Perform. Cogn. Eng. Res. pp. 1–12 (2002). https://doi.org/10.1016/S1479-3601(02)02003-9
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 preprint arXiv:1902.01876 (2019)
Hoffman, R.R., Klein, G., Mueller, S.T.: Explaining explanation for “Explainable Ai”. Proc. Hum. Factors Ergon. Soc. Annu. Meet. 62, 197–201 (2018). https://doi.org/10.1177/1541931218621047
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Schrills, T., Franke, T. (2020). Color for Characters - Effects of Visual Explanations of AI on Trust and Observability. In: Degen, H., Reinerman-Jones, L. (eds) Artificial Intelligence in HCI. HCII 2020. Lecture Notes in Computer Science(), vol 12217. Springer, Cham. https://doi.org/10.1007/978-3-030-50334-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-50334-5_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-50333-8
Online ISBN: 978-3-030-50334-5
eBook Packages: Computer ScienceComputer Science (R0)