Abstract
[Context and Motivation] Recent studies have highlighted transparency and explainability as important quality requirements of AI systems. However, there are still relatively few case studies that describe the current state of defining these quality requirements in practice. [Question] The goal of our study was to explore what ethical guidelines organizations have defined for the development of transparent and explainable AI systems. We analyzed the ethical guidelines in 16 organizations representing different industries and public sector. [Results] In the ethical guidelines, the importance of transparency was highlighted by almost all of the organizations, and explainability was considered as an integral part of transparency. Building trust in AI systems was one of the key reasons for developing transparency and explainability, and customers and users were raised as the main target groups of the explanations. The organizations also mentioned developers, partners, and stakeholders as important groups needing explanations. The ethical guidelines contained the following aspects of the AI system that should be explained: the purpose, role of AI, inputs, behavior, data utilized, outputs, and limitations. The guidelines also pointed out that transparency and explainability relate to several other quality requirements, such as trustworthiness, understandability, traceability, privacy, auditability, and fairness. [Contribution] For researchers, this paper provides insights into what organizations consider important in the transparency and, in particular, explainability of AI systems. For practitioners, this study suggests a structured way to define explainability requirements of AI systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdollahi, B., Nasraoui, O.: Transparency in fair machine learning: the case of explainable recommender systems. In: Zhou, J., Chen, F. (eds.) Human and Machine Learning. HIS, pp. 21–35. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-90403-0_2
Ahmad, K., Bano, M., Abdelrazek, M., Arora, C., Grundy, J.: What’s up with requirements engineering for artificial intelligent systems? In: International Requirements Engineering Conference, pp. 1–12 (2021)
Balasubramaniam, N., Kauppinen, M., Kujala, S., Hiekkanen, K.: Ethical guidelines for solving ethical issues and developing AI systems. In: Morisio, M., Torchiano, M., Jedlitschka, A. (eds.) PROFES 2020. LNCS, vol. 12562, pp. 331–346. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-64148-1_21
Charmaz, K.: Constructing Grounded Theory, 2nd edn. SAGE Publications Inc., Thousand Oaks (2014)
Chazette, L.: Mitigating challenges in the elicitation and analysis of transparency requirements. In: International Requirements Engineering Conference, pp. 470–475 (2019)
Chazette, L., Brunotte, W., Speith, T.: Exploring explainability: a definition, a model, and a knowledge catalogue. In: International Requirements Engineering Conference, pp. 197–208 (2021)
Chazette, L., Karras, O., Schneider, K.: Do end-users want explanations? Analyzing the role of explainability as an emerging aspect of non-functional requirements. In: International Requirements Engineering Conference, pp. 223–233 (2019)
Chazette, L., Schneider, K.: Explainability as a non-functional requirement: challenges and recommendations. Requirements Eng. 25(4), 493–514 (2020). https://doi.org/10.1007/s00766-020-00333-1
Cohn, M.: Agile Estimating and Planning. Prentice Hall, Upper Saddle River (2006)
Corbin, J., Strauss, A.: Basics of Qualitative Research, 4th edn. SAGE, Thousand Oaks (2015)
Cysneiros, L.M.: Using i* to elicit and model transparency in the presence of other non-functional requirements: a position paper. In: iStar: Citeseer, pp. 19–24 (2013)
Cysneiros, L., do Prado, J.: Non-functional requirements orienting the development of socially responsible software. In: Nurcan, S., Reinhartz, I., Soffer, P., Zdravkovic, J. (eds.) BPMDS/EMMSAD - 2020. LNBIP, vol. 387, pp. 335–342. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-49418-6_23
Cysneiros, L.M., Raffi, M., Sampaio do Prado Leite, J.C.: Software transparency as a key requirement for self-driving cars. In: International Requirements Engineering Conference, pp. 382–387 (2018)
do Prado Leite, J.C.S., Cappelli, C.: Software transparency. Business Inf. Syst. Eng. 2(3), 127–139 (2010)
Drobotowicz, K., Kauppinen, M., Kujala, S.: Trustworthy AI services in the public sector: what are citizens saying about it? In: Requirements Engineering: Foundation for Software Quality, pp. 99–115 (2021)
European Commission: Ethics Guidelines for Trustworthy AI. https://ec.europa.eu/futurium/en/ai-alliance-consultation/guidelines. Accessed 24 Oct 2021
Guizzardi, R., Amaral, G., Guizzardi, G., Mylopoulos, J.: Ethical requirements for AI systems. In: Goutte, C., Zhu, X. (eds.) Canadian AI 2020. LNCS (LNAI), vol. 12109, pp. 251–256. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-47358-7_24
Habibullah, K.M., Horkoff, J.: Non-functional requirements for machine learning: understanding current use and challenges in industry. In: International Requirements Engineering Conference, pp. 13–23 (2021)
Horkoff, J.: Non-functional requirements for machine learning: challenges and new directions. In: International Requirements Engineering Conference, pp. 386–391 (2019)
IEEE: Ethically Aligned Design, 1st edn. https://ethicsinaction.ieee.org/. Accessed 24 Oct 2021
Kwan, D., Cysneiros, L.M., do Prado Leite, J.C.S.: Towards Achieving Trust Through Transparency and Ethics (Pre-Print) (2021). http://arxiv.org/abs/2107.02959. Accessed 30 Aug 2021
Köhl, M.A., Baum, K., Langer, M., Oster, D., Speith, T., Bohlender, D.: Explainability as a non-functional requirement. In: International Requirements Engineering Conference, pp. 363–368 (2019)
Lepri, B., Oliver, N., Letouzé, E., Pentland, A., Vinck, P.: Fair, transparent, and accountable algorithmic decision-making processes. Philos. Technol. 31(4), 611–627 (2018)
Paech, B., Schneider, K.: How do users talk about software? Searching for common ground. In: Workshop on Ethics in Requirements Engineering Research and Practice, pp. 11–14 (2020)
SIIA (Software and Information Industry Association): Ethical Principles for Artificial Intelligence and Data Analytics, pp. 1–25 (2017)
Zieni, B., Heckel, R.: TEM: a transparency engineering methodology enabling users’ trust judgement. In: International Requirements Engineering Conference, pp. 94–105 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Balasubramaniam, N., Kauppinen, M., Hiekkanen, K., Kujala, S. (2022). Transparency and Explainability of AI Systems: Ethical Guidelines in Practice. In: Gervasi, V., Vogelsang, A. (eds) Requirements Engineering: Foundation for Software Quality. REFSQ 2022. Lecture Notes in Computer Science, vol 13216. Springer, Cham. https://doi.org/10.1007/978-3-030-98464-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-98464-9_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-98463-2
Online ISBN: 978-3-030-98464-9
eBook Packages: Computer ScienceComputer Science (R0)