Abstract
Artificial intelligence algorithms – and data that feed them – are increasingly imbued with agency and impact and are empowered to make decisions in our lives in a wide variety of domains: from search engines, information filtering, political campaigns, health to the prediction of criminal recidivism or loan repayment. Indeed, algorithms are difficult to understand, and explaining “how they exercise their power and influence” and how a given input (whether or not consciously released) is transformed into an output. In the computer science field, techniques of explainable artificial intelligence (XAI) have been developed for disclosing and studying algorithmic models, using data visualization as visual language to let experts explore their inner workings. However, current research on machine learning explainability empowers the creators of machine learning models but is not addressing the needs of people affected by them. This paper leverages on communication and information design methods (or competences) to expand the explainable machine learning field of action towards the general public.
The term artifact is intended as a man-made object.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Diakopoulos, N.: Algorithmic accountability: journalistic investigation of computational power structures. Digit. J. 3(3), 398–415 (2015)
Gillespie, T.: The Relevance of Algorithms. Media Technol., no. Light 1999, pp. 167–194 (2014)
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous distributed systems. arXiv preprint arXiv:1603.04467 (2016)
Strobelt, H., Gehrmann, S., Behrisch, M., Perer, A., Pfister, H., Rush, A.M.: Seq2Seq-Vis: a visual debugging tool for sequence-to-sequence models. IEEE Trans. Vis. Comput. Graph. 25(1), 353–363 (2018)
Barron, W.: Teachable Machine Tutorial: Bananameter. Medium, Sep
Ziewitz, M.: Governing algorithms: myth, mess, and methods. Sci. Technol. Hum. Values 41(1), 3–16 (2016)
Correll, M.: Ethical dimensions of visualization research. In: Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, pp. 1–13 (2019)
Baule, G., Caratti, E.: Towards translation design a new paradigm for design research. Futur. Think., pp. 1–14 2016
Vande Moere, A., Purchase, H.: On the role of design in information visualization. Inf. Vis. 10(4), 356–371 (2011)
Kolkman, D.: The (in) credibility of algorithmic models to non- experts. Inf. Commun. Soc. 4462, 1–17 (2020)
Jentner, W., Sevastjanova, R., Stoffel, F., Keim, D.A., Bernard, J., El-Assady, M.: Minions, sheep, and fruits: metaphorical narratives to explain artificial intelligence and build trust. In: Workshop on Visualization for AI Explainability at IEEE (2018)
El-Assady, M., Jentner, W., Kehlbeck, R., Schlegel, U.: Towards XAI : structuring the processes of explanations. (2019)
Sevastjanova, R., et al.: Going beyond visualization: verbalization as complementary medium to explain machine learning models. In: Workshop on Visualization for AI Explainability at IEEE VIS (2018)
Zingale, S.: Interpretazione e progetto. semiotica dell’inventiva (2012)
Crawford, K., Joler, V.: Anatomy of an AI system
Share Lab: The Human Fabric of the Facebook Pyramid. https://labs.rs/en/category/facebook-research/
Atken, M.: Gloomy Sunday. (2017). http://www.memo.tv/works/gloomy-sunday/
Atken, M.: Optimising for beauty (2017). http://www.memo.tv/works/optimising-for-beauty/
Google Creative Lab: Quick, Draw (2017). https://experiments.withgoogle.com/quick-draw
Google AI: Semantris (2018). https://experiments.withgoogle.com/semantris
Invernizzi, M., Ciuccarelli, P.: Visual monitoring of complex algorithms. In: 2CO Communication Complexity Contribution from 2017 Tenerife Conference, pp. 115–120 (2020)
Beaman, H., Campagna, T., Mniestri, A. Rossetti, G., Wang, X., Durand, R.: Tracking gender bias in amazon search results (2020)
Buolamwini, J., Gebru, T.: Gender shades: intersectional accuracy disparities in commercial gender classificatio. In: Conference on Fairness, Accountability and Transparency, pp. 77–91 (2017)
Cattaneo, A., et al.: DeepfakeLab (2020) https://deepfakelab.theglassroom.org
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
Gobbo, B. (2021). Explaining AI Through Critical Reflection Artifacts. In: Reis, T., Bornschlegl, M.X., Angelini, M., Hemmje, M.L. (eds) Advanced Visual Interfaces. Supporting Artificial Intelligence and Big Data Applications. AVI-BDA ITAVIS 2020 2020. Lecture Notes in Computer Science(), vol 12585. Springer, Cham. https://doi.org/10.1007/978-3-030-68007-7_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-68007-7_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-68006-0
Online ISBN: 978-3-030-68007-7
eBook Packages: Computer ScienceComputer Science (R0)