Effects of Influence on User Trust in Predictive Decision Making

ABSTRACT

This paper introduces fact-checking into Machine Learning (ML) explanation by referring training data points as facts to users to boost user trust. We aim to investigate what influence of training data points, and how they affect user trust in order to enhance ML explanation and boost user trust. We tackle this question by allowing users check the training data points that have the higher influence and the lower influence on the prediction. A user study found that the presentation of influences significantly increases the user trust in predictions, but only for training data points with higher influence values under the high model performance condition, where users can justify their actions with more similar facts.

References

1. Or Biran and Kathleen McKeown. 2017. Human-centric Justification of Machine Learning Predictions. In Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI'17). 1461--1467.
2. Pang Wei Koh and Percy Liang. 2017. Understanding Black-box Predictions via Influence Functions. In Proceedings of the 34th International Conference on Machine Learning, ICML 2017. Sydney, NSW, Australia, 1885--1894.
3. Travis Kriplean, Caitlin Bonnar, Alan Borning, Bo Kinney, and Brian Gill. 2014. Integrating On-demand Fact-checking with Public Dialogue. In Proceedings of the 17th ACM Conference on Computer Supported Cooperative Work & Social Computing (CSCW '14). 1188--1199.
4. Panagiotis Symeonidis, Alexandros Nanopoulos, and Yannis Manolopoulos. 2009. MoviExplain: A Recommender System with Explanations. In Proceedings of the Third ACM Conference on Recommender Systems. 317--320.
5. L. Richard Ye and Paul E. Johnson. 1995. The Impact of Explanation Facilities on User Acceptance of Expert Systems Advice. MIS Quarterly 19, 2 (June 1995), 157--172.
6. Jianlong Zhou and Fang Chen. 2018. DecisionMind: revealing human cognition states in data analytics-driven decision making with a multimodal interface. Journal of Multimodal User Interfaces 12, 2 (2018), 67--76.
7. Jianlong Zhou and Fang Chen (Eds.). 2018. Human and Machine Learning: Visible, Explainable, Trustworthy and Transparent. Springer, Cham.
8. Jianlong Zhou, M. Asif Khawaja, Zhidong Li, Jinjun Sun, Yang Wang, and Fang Chen. 2016. Making Machine Learning Useable by Revealing Internal States Update -- A Transparent Approach. International Journal of Computational Science and Engineering 13, 4 (2016), 378--389.
9. Jianlong Zhou, Zelin Li, Weiming Zhi, Bin Liang, Daniel Moses, and Laughlin Dawes. 2017. Using Convolutional Neural Networks and Transfer Learning for Bone Age Classification. In 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA 2017). 1--6.
10. Jianlong Zhou, Jinjun Sun, Yang Wang, and Fang Chen. 2017. Wrapping Practical Problems into a Machine Learning Framework: Using Water Pipe Failure Prediction As a Case Study. International Journal of Intelligent Systems Technologies and Applications 16, 3 (2017), 191--207.

Index Terms

• Human-centered computing

  • Human computer interaction (HCI)

    • Empirical studies in HCI