ABSTRACT
Increasingly, algorithms are used to make important decisions across society. However, these algorithms are usually poorly understood, which can reduce transparency and evoke negative emotions. In this research, we seek to learn design principles for explanation interfaces that communicate how decision-making algorithms work, in order to help organizations explain their decisions to stakeholders, or to support users' "right to explanation". We conducted an online experiment where 199 participants used different explanation interfaces to understand an algorithm for making university admissions decisions. We measured users' objective and self-reported understanding of the algorithm. Our results show that both interactive explanations and "white-box" explanations (i.e. that show the inner workings of an algorithm) can improve users' comprehension. Although the interactive approach is more effective at improving comprehension, it comes with a trade-off of taking more time. Surprisingly, we also find that users' trust in algorithmic decisions is not affected by the explanation interface or their level of comprehension of the algorithm.
Supplemental Material
Available for Download
The auxiliary file contains a PDF document (ExplainingDecisionMakingAlgorithmsThroughUI_survey.pdf). The document includes the original survey used in the study.
- Ashraf Abdul, Jo Vermeulen, Danding Wang, Brian Y Lim, and Mohan Kankanhalli. 2018. 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. ACM, 582. Google ScholarDigital Library
- Saleema Amershi, Max Chickering, Steven M Drucker, Bongshin Lee, Patrice Simard, and Jina Suh. 2015. Modeltracker: Redesigning performance analysis tools for machine learning. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. ACM, 337--346. Google ScholarDigital Library
- Julia Angwin. 2016. Make algorithms accountable. The New York Times 1 (2016), 168.Google Scholar
- Barry Becker, Ron Kohavi, and Dan Sommerfield. 2002. Visualizing the Simple Bayesian Classifier. In Information visualization in data mining and knowledge discovery. Morgan Kaufmann, 237--249. Google ScholarDigital Library
- Victoria Bellotti and Keith Edwards. 2001. Intelligibility and accountability: human considerations in context-aware systems. Human-- Computer Interaction 16, 2--4 (2001), 193--212. Google ScholarDigital Library
- Or Biran and Courtenay Cotton. 2017. Explanation and justification in machine learning: A survey. In IJCAI-17 Workshop on Explainable AI (XAI). 8. Explaining Decision-Making Algorithms through UI CHI 2019, May 4--9, 2019, Glasgow, Scotland UkGoogle Scholar
- Jenna Burrell. 2016. How the machine 'thinks': Understanding opacity in machine learning algorithms. Big Data & Society 3, 1 (2016), 2053951715622512.Google ScholarCross Ref
- Ángel Cabrera, Fred Hohman, Jason Lin, and Duen Horng Chau. 2018. Interactive Classification for Deep Learning Interpretation. arXiv preprint arXiv:1806.05660 (2018).Google Scholar
- Doina Caragea, Dianne Cook, and Vasant G Honavar. 2001. Gaining insights into support vector machine pattern classifiers using projection-based tour methods. In Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 251--256. Google ScholarDigital Library
- Alexandra Chouldechova, Diana Benavides-Prado, Oleksandr Fialko, and Rhema Vaithianathan. 2018. A case study of algorithm-assisted decision making in child maltreatment hotline screening decisions. In Conference on Fairness, Accountability and Transparency. 134--148.Google Scholar
- Sam Corbett-Davies, Emma Pierson, Avi Feller, Sharad Goel, and Aziz Huq. 2017. Algorithmic decision making and the cost of fairness. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 797--806. Google ScholarDigital Library
- Cynthia L Corritore, Beverly Kracher, and Susan Wiedenbeck. 2003. On-line trust: concepts, evolving themes, a model. International journal of human-computer studies 58, 6 (2003), 737--758. Google ScholarDigital Library
- Mark Craven and Jude Shavlik. 1999. Rule extraction: Where do we go from here. University of Wisconsin Machine Learning Research Group working Paper 99 (1999).Google Scholar
- Michael A DeVito, Jeremy Birnholtz, and Jeffery T Hancock. 2017. Platforms, people, and perception: Using affordances to understand self-presentation on social media. In Proceedings of the 2017 ACM Conference on Computer Supported Cooperative Work and Social Computing. ACM, 740--754. Google ScholarDigital Library
- Michael A DeVito, Jeffrey T Hancock, Megan French, Jeremy Birnholtz, Judd Antin, Karrie Karahalios, Stephanie Tong, and Irina Shklovski. 2018. The Algorithm and the User: How Can HCI Use Lay Understandings of Algorithmic Systems?. In Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems. ACM, panel04. Google ScholarDigital Library
- Nicholas Diakopoulos. 2016. Accountability in algorithmic decision making. Commun. ACM 59, 2 (2016), 56--62. Google ScholarDigital Library
- Berkeley J Dietvorst, Joseph P Simmons, and Cade Massey. 2015. Algorithm aversion: People erroneously avoid algorithms after seeing them err. Journal of Experimental Psychology: General 144, 1 (2015), 114.Google ScholarCross Ref
- Finale Doshi-Velez and Been Kim. 2017. A roadmap for a rigorous science of interpretability. arXiv preprint. arXiv preprint arXiv:1702.08608 (2017).Google Scholar
- Julia Dressel and Hany Farid. 2018. The accuracy, fairness, and limits of predicting recidivism. Science advances 4, 1 (2018), eaao5580.Google Scholar
- Motahhare Eslami, Karrie Karahalios, Christian Sandvig, Kristen Vaccaro, Aimee Rickman, Kevin Hamilton, and Alex Kirlik. 2016. First i like it, then i hide it: Folk theories of social feeds. In Proceedings of the 2016 cHI conference on human factors in computing systems. ACM, 2371--2382. Google ScholarDigital Library
- Megan French and Jeff Hancock. 2017. What's the folk theory? Reasoning about cyber-social systems. (2017).Google Scholar
- Nahum Gershon. 1998. Visualization of an imperfect world. IEEE Computer Graphics and Applications 4 (1998), 43--45. Google ScholarDigital Library
- Bryce Goodman and Seth Flaxman. 2016. European Union regulations on algorithmic decision-making and a "right to explanation". arXiv preprint arXiv:1606.08813 (2016).Google Scholar
- Spence Green, Jason Chuang, Jeffrey Heer, and Christopher D Manning. 2014. Predictive Translation Memory: A mixed-initiative system for human language translation. In Proceedings of the 27th annual ACM symposium on User interface software and technology. ACM, 177--187. Google ScholarDigital Library
- Paul Hitlin. 2016. Research in the crowdsourcing age, a case study. Pew Research Center 11 (2016).Google Scholar
- Fred Matthew Hohman, Minsuk Kahng, Robert Pienta, and Duen Horng Chau. 2018. Visual Analytics in Deep Learning: An Interrogative Survey for the Next Frontiers. IEEE Transactions on Visualization and Computer Graphics (2018).Google ScholarDigital Library
- Eric Horvitz. 1999. Principles of mixed-initiative user interfaces. In Proceedings of the SIGCHI conference on Human Factors in Computing Systems. ACM, 159--166. Google ScholarDigital Library
- Aleks Jakulin, Martin Moina, Janez Demsar, Ivan Bratko, and Blaz Zupan. 2005. Nomograms for visualizing support vector machines. In Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining. ACM, 108--117. Google ScholarDigital Library
- Mary Beth Kery, Amber Horvath, and Brad A Myers. 2017. Variolite: Supporting Exploratory Programming by Data Scientists.. In CHI. 1265-- 1276. Google ScholarDigital Library
- Jon Kleinberg, Himabindu Lakkaraju, Jure Leskovec, Jens Ludwig, and Sendhil Mullainathan. 2017. Human decisions and machine predictions. The quarterly journal of economics 133, 1 (2017), 237--293.Google ScholarCross Ref
- Josua Krause, Adam Perer, and Kenney Ng. 2016. Interacting with predictions: Visual inspection of black-box machine learning models. In Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems. ACM, 5686--5697. Google ScholarDigital Library
- John Lee and Neville Moray. 1992. Trust, control strategies and allocation of function in human-machine systems. Ergonomics 35, 10 (1992), 1243--1270.Google ScholarCross Ref
- Min Kyung Lee and Su Baykal. 2017. Algorithmic Mediation in Group Decisions: Fairness Perceptions of Algorithmically Mediated vs. Discussion-Based Social Division.. In CSCW. 1035--1048. Google ScholarDigital Library
- Brian Y Lim. 2012. Improving understanding and trust with intelligibility in context-aware applications. (2012).Google Scholar
- Zachary C Lipton. 2016. The mythos of model interpretability. arXiv preprint arXiv:1606.03490 (2016).Google Scholar
- David Martens and Foster Provost. 2013. Explaining data-driven document classifications. (2013).Google Scholar
- Adam W Meade and S Bartholomew Craig. 2012. Identifying careless responses in survey data. Psychological methods 17, 3 (2012), 437.Google Scholar
- Tim Miller. 2017. Explanation in artificial intelligence: insights from the social sciences. arXiv preprint arXiv:1706.07269 (2017).Google Scholar
- Julian D Olden and Donald A Jackson. 2002. Illuminating the "black box": a randomization approach for understanding variable contributions in artificial neural networks. Ecological modelling 154, 1--2 (2002), 135--150.Google Scholar
- Cathy O'Neil. 2016. Weapons of math destruction: How big data increases inequality and threatens democracy. Broadway Books. Google Scholar
- Kayur Patel, Steven M Drucker, James Fogarty, Ashish Kapoor, and Desney S Tan. 2011. Using multiple models to understand data. In IJCAI Proceedings-International Joint Conference on Artificial Intelligence, Vol. 22. 1723. Google ScholarDigital Library
- Yi Peng, Guoxun Wang, Gang Kou, and Yong Shi. 2011. An empirical study of classification algorithm evaluation for financial risk prediction. Applied Soft Computing 11, 2 (2011), 2906--2915. Google ScholarDigital Library
- Tony A Plate, Joel Bert, John Grace, and Pierre Band. 2000. Visualizing the function computed by a feedforward neural network. Neural computation 12, 6 (2000), 1337--1353. Google ScholarDigital Library
- Donghao Ren, Saleema Amershi, Bongshin Lee, Jina Suh, and Jason D Williams. 2017. Squares: Supporting interactive performance analysis for multiclass classifiers. IEEE transactions on visualization and computer graphics 23, 1 (2017), 61--70. Google ScholarDigital Library
- Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. Why should i trust you?: Explaining the predictions of any classifier. In CHI 2019, May 4--9, 2019, Glasgow, Scotland Uk Hao-Fei Cheng et al. Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, 1135--1144. Google ScholarDigital Library
- Daniel Smilkov, Shan Carter, D Sculley, Fernanda B Viégas, and Martin Wattenberg. 2017. Direct-manipulation visualization of deep networks. arXiv preprint arXiv:1708.03788 (2017).Google Scholar
- Simone Stumpf, Vidya Rajaram, Lida Li, Weng-Keen Wong, Margaret Burnett, Thomas Dietterich, Erin Sullivan, and Jonathan Herlocker. 2009. Interacting meaningfully with machine learning systems: Three experiments. International Journal of Human-Computer Studies 67, 8 (2009), 639--662. Google ScholarDigital Library
- Sebastian Thrun. 1995. Extracting rules from artificial neural networks with distributed representations. In Advances in neural information processing systems. 505--512. Google ScholarDigital Library
- Meng-Jung Tsai, Ching-Yeh Wang, and Po-Fen Hsu. {n. d.}. Developing the Computer Programming Self-Efficacy Scale for Computer Literacy Education. Journal of Educational Computing Research ({n. d.}), 0735633117746747.Google Scholar
- F-Y Tzeng and K-L Ma. 2002. Opening the black box-data driven visualization of neural networks. 383--390 pages.Google Scholar
- Sandra Wachter, Brent Mittelstadt, and Luciano Floridi. 2017. Why a right to explanation of automated decision-making does not exist in the general data protection regulation. International Data Privacy Law 7, 2 (2017), 76--99.Google ScholarCross Ref
- Lauren Weber and RE Silverman. 2012. Your resume vs. oblivion. The Wall Street Journal 24 (2012).Google Scholar
- Daniel S Weld and Gagan Bansal. 2018. Intelligible Artificial Intelligence. arXiv preprint arXiv:1803.04263 (2018).Google Scholar
- Ann Wilkinson, Alison E While, and Julia Roberts. 2009. Measurement of information and communication technology experience and attitudes to e-learning of students in the healthcare professions: integrative review. Journal of advanced nursing 65, 4 (2009), 755--772.Google ScholarCross Ref
Index Terms
- Explaining Decision-Making Algorithms through UI: Strategies to Help Non-Expert Stakeholders
Recommendations
On the Impact of Explanations on Understanding of Algorithmic Decision-Making
FAccT '23: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and TransparencyEthical principles for algorithms are gaining importance as more and more stakeholders are affected by "high-risk" algorithmic decision-making (ADM) systems. Understanding how these systems work enables stakeholders to make informed decisions and to ...
A Framework of High-Stakes Algorithmic Decision-Making for the Public Sector Developed through a Case Study of Child-Welfare
CSCW2Algorithms have permeated throughout civil government and society, where they are being used to make high-stakes decisions about human lives. In this paper, we first develop a cohesive framework of algorithmic decision-making adapted for the public ...
Trust-inspiring explanation interfaces for recommender systems
A recommender system's ability to establish trust with users and convince them of its recommendations, such as which camera or PC to purchase, is a crucial design factor especially for e-commerce environments. This observation led us to build a trust ...
Comments