Abstract
Machine Learning (ML) models are increasingly being used in many sectors, ranging from health and education to justice and criminal investigation. Therefore, building a fair and transparent model which conveys the reasoning behind its predictions is of great importance. This chapter discusses the role of explanation mechanisms in building fair machine learning models and explainable ML technique. We focus on the special case of recommender systems because they are a prominent example of a ML model that interacts directly with humans. This is in contrast to many other traditional decision making systems that interact with experts (e.g. in the health-care domain). In addition, we discuss the main sources of bias that can lead to biased and unfair models. We then review the taxonomy of explanation styles for recommender systems and review models that can provide explanations for their recommendations. We conclude by reviewing evaluation metrics for assessing the power of explainability in recommender systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdollahi, B., Nasraoui, O.: Explainable Matrix Factorization for Collaborative Filtering. In: Proceedings of the 25th International Conference Companion on World Wide Web. International World Wide Web Conferences Steering Committee (2016)
Abdollahi, B., Nasraoui, O.: Explainable Restricted Boltzmann Machines for Collaborative Filtering (2016). arXiv preprint arXiv:1606.07129
Abdollahi, B., Nasraoui, O.: Using Explainability for Constrained Matrix Factorization. In: Proceedings of the Eleventh ACM Conference on Recommender Systems, pp. 79–83. ACM (2017)
Antunes, P., Herskovic, V., Ochoa, S.F., Pino, J.A.: Structuring dimensions for collaborative systems evaluation. ACM Comput. Surv. (CSUR) 44(2), 8 (2012)
Ardissono, L., Goy, A., Petrone, G., Segnan, M., Torasso, P.: Intrigue: personalized recommendation of tourist attractions for desktop and hand held devices. Appl. Artif. Intell. 17(8–9), 687–714 (2003)
Baeza-Yates, R.: Data and algorithmic bias in the web. In: Proceedings of the 8th ACM Conference on Web Science, pp. 1–1. ACM (2016)
Beede, D.N., Julian, T.A., Langdon, D., McKittrick, G., Khan, B., Doms, M.E.: Women in STEM: A Gender Gap to Innovation (2011)
Bilgic, M., Mooney, R.J.: Explaining recommendations: satisfaction versus promotion. In: Beyond Personalization Workshop, IUI, vol. 5, 153 p. (2005)
Billsus, D., Pazzani, M. J.: A personal news agent that talks, learns and explains. In: Proceedings of the Third Annual Conference on Autonomous Agents, pp. 268–275. ACM (1999)
Brown, B., Aaron, M.: The politics of nature. In: Smith, J. (ed.) The Rise of Modern Genomics, 3rd edn. Wiley, New York (2001)
Broy, M.: Software engineering – from auxiliary to key technologies. In: Broy, M., Dener, E. (eds.). Software Pioneers, pp. 10–13. Springer, Berlin (2002)
Calfee, R.C., Valencia, R.R.: APA guide to preparing manuscripts for journal publication. American Psychological Association, Washington, DC (1991)
Cameron, D.: Feminism and Linguistic Theory. St. Martin’s Press, New York (1985)
Cameron, D.: Theoretical debates in feminist linguistics: questions of sex and gender. In: Wodak, R. (ed.) Gender and Discourse, pp. 99–119. Sage Publications, London (1997)
Dascalu, M.I., Bodea, C.N., Mihailescu, M.N., Tanase, E.A., Ordoez de Pablos, P.: Educational recommender systems and their application in lifelong learning. Behav. Inf. Technol. 35(4), 290–297 (2016)
Dod, J.: Effective substances. In: The Dictionary of Substances and Their Effects. Royal Society of Chemistry (1999) Available via DIALOG. http://www.rsc.org/dose/titleofsubordinatedocument. Cited 15 Jan 1999
Dod, J.: Effective substances. In: The dictionary of substances and their effects. Royal Society of Chemistry (1999). Available via DIALOG. http://www.rsc.org/dose/Effectivesubstances. Cited 15 Jan 1999
Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning (2017)
Dwork, C.: What’s Fair?. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1–1. ACM (2017)
Fish, B., Kun, J., Lelkes, D.: A confidence-based approach for balancing fairness and accuracy. In: Proceedings of the 2016 SIAM International Conference on Data Mining, pp. 144–152. Society for Industrial and Applied Mathematics (2016)
Freitas, A.A.: Comprehensible classification models: a position paper. ACM SIGKDD Explor. Newsl. 15(1), 1–10 (2014)
Geddes, K.O., Czapor, S.R., Labahn, G.: Algorithms for Computer Algebra. Kluwer, Boston (1992)
Griffith, A.L.: Persistence of women and minorities in STEM field majors: is it the school that matters? Econ. Educ. Rev. 29(6), 911–922 (2010)
Hajian, S., Bonchi, F., Castillo, C.: Algorithmic bias: from discrimination discovery to fairness-aware data mining. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 2125–2126. ACM (2016)
Hamburger, C.: Quasimonotonicity, regularity and duality for nonlinear systems of partial differential equations. Ann. Mat. Pura. Appl. 169, 321–354 (1995)
Hardt, M., Price, E., Srebro, N.: Equality of opportunity in supervised learning. In: Advances in Neural Information Processing Systems, pp. 3315–3323 (2016)
Harper, F.M., Konstan, J.A.: The movielens datasets: history and context. ACM Trans. Interact. Intell. Syst. (TiiS) 5(4), 19 (2016)
Harris, M., Karper, E., Stacks, G., Hoffman, D., DeNiro, R., Cruz, P., et al.: Writing labs and the Hollywood connection. J Film Writing 44(3), 213–245 (2001)
Herlocker, J.L., Konstan, J.A., Riedl, J.: Explaining collaborative filtering recommendations. In: Proceedings of the 2000 ACM Conference on Computer Supported Cooperative Work, pp. 241–250. ACM (2000)
Ibach, H., Lüth, H.: Solid-State Physics, 2nd edn, pp. 45–56. Springer, New York (1996)
John, Alber, O’Connell, Daniel C., Kowal, Sabine: Personal perspective in TV interviews. Pragmatics 12, 257–271 (2002)
Kamiran, F., Calders, T.: Classifying without discriminating. In: 2nd International Conference on Computer, Control and Communication, 2009. IC4 2009, pp. 1-6). IEEE, New York (2009)
Kamishima T., Akaho, S., Sakuma, J.: Fairness-aware learning through regularization approach. In: 2011 IEEE 11th International Conference on Data Mining Workshops (ICDMW), pp. 643–650. IEEE, New York (2011)
Kleinberg, J., Mullainathan, S., Raghavan, M.: Inherent trade-offs in the fair determination of risk scores (2016). arXiv preprint arXiv:1609.05807
Kreger, M., Brindis, C.D., Manuel, D.M., Sassoubre, L. (2007). Lessons learned in systems change initiatives: benchmarks and indicators. Am. J. Commun. Psychol. https://doi.org/10.1007/s10464-007-9108-14
Lipton, Z.C.: The Mythos of Model Interpretability (2016). arXiv preprint arXiv:1606.03490
McCarthy, K., Reilly, J., McGinty, L., Smyth, B.: Thinking positively-explanatory feedback for conversational recommender systems. In: Proceedings of the European Conference on Case-Based Reasoning (ECCBR-04) Explanation Workshop, pp. 115–124 (2004)
O’Neil, J.M., Egan, J.: Men’s and women’s gender role journeys: metaphor for healing, transition, and transformation. In: Wainrig, B.R. (ed.) Gender Issues Across the Life Cycle, pp. 107–123. Springer, New York (1992)
Pohl, R. (ed.).: Cognitive Illusions: A Handbook on Fallacies and Biases in Thinking, Judgement and Memory. Psychology Press (2004)
S. Preuss, A. Demchuk Jr., M. Stuke, Appl. Phys. A 61 (1995)
Pu, P., Chen, L., Hu, R.: A user-centric evaluation framework for recommender systems. In: Proceedings of the Fifth ACM Conference on Recommender Systems, pp. 157–164. ACM, Chicago (2011)
Ribeiro, M.T., Singh, S., Guestrin, C.: Why should i trust you?: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135-1144. ACM (2016)
Sapiezynski, P., Kassarnig, V., Wilson, C.: Academic performance prediction in a gender-imbalanced environment (2017)
Sharma, A., Cosley, D.: Do social explanations work?: studying and modeling the effects of social explanations in recommender systems. In: Proceedings of the 22nd International Conference on World Wide Web, pp. 1133–1144. ACM (2013)
Slifka, M.K., Whitton, J.L.: Clinical implications of dysregulated cytokine production. J. Mol. Med. (2000). https://doi.org/10.1007/s001090000086
Slifka, M.K., Whitton, J.L.: Clinical implications of dysregulated cytokine production. J. Mol. Med. (2000). https://doi.org/10.1007/s001090000086
M.K. Slifka, J.L. Whitton, J. Mol. Med. https://doi.org/10.1007/s001090000086
S.E. Smith, in Neuromuscular Junction, ed. by E. Zaimis. Handbook of Experimental Pharmacology, vol 42 (Springer, Heidelberg, 1976), p. 593
Smith, E.: Women into science and engineering? gendered participation in higher education STEM subjects. Br. Educ. Res. J. 37(6), 993–1014 (2011)
Smith, J., Jones Jr., M., Houghton, L., et al.: Future of health insurance. N. Eng. J. Med. 965, 325–329 (1999)
South, J., Blass, B.: The Future of Modern Genomics. Blackwell, London (2001)
Suleiman, C., O’Connell, D.C., Kowal, S.: If you and I, if we, in this later day, lose that sacred fire...’: Perspective in political interviews. J. Psycholinguist. Res. (2002). https://doi.org/10.1023/A:1015592129296
Symeonidis, P., Nanopoulos, A., Manolopoulos, Y.: Justified recommendations based on content and rating data. In: WebKDD Workshop on Web Mining and Web Usage Analysis (2008)
Thai-Nghe, N., Drumond, L., Krohn-Grimberghe, A., Schmidt-Thieme, L.: Recommender system for predicting student performance. Procedia Comput. Sci. 1(2), 2811–2819 (2010)
Tintarev, N., Masthoff, J.: Designing and evaluating explanations for recommender systems. In: Recommender Systems Handbook, pp. 479–510 (2011)
Tintarev, N., Masthoff, J.: Evaluating the effectiveness of explanations for recommender systems. User Model. User-Adap. Inter. 22(4), 399–439 (2012)
Vig, J., Sen, S., Riedl, J.: Tagsplanations: explaining recommendations using tags. In: Proceedings of the 14th International Conference on Intelligent User Interfaces, pp. 47–56. ACM (2009)
Yao, S., Huang, B.: New Fairness Metrics for Recommendation that Embrace Differences (2017). arXiv preprint arXiv:1706.09838
Zhang, Y., Lai, G., Zhang, M., Zhang, Y., Liu, Y., Ma, S.: Explicit factor models for explainable recommendation based on phrase-level sentiment analysis. In: Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 83–92. ACM (2014)
Acknowledgements
This research was partially supported by KSEF Award KSEF-3113-RDE-017 and NSF Grant NSF IIS-1549981.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this chapter
Cite this chapter
Abdollahi, B., Nasraoui, O. (2018). Transparency in Fair Machine Learning: the Case of Explainable Recommender Systems. In: Zhou, J., Chen, F. (eds) Human and Machine Learning. Human–Computer Interaction Series. Springer, Cham. https://doi.org/10.1007/978-3-319-90403-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-90403-0_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-90402-3
Online ISBN: 978-3-319-90403-0
eBook Packages: Computer ScienceComputer Science (R0)