Log In Sign Up

"I had a solid theory before but it's falling apart": Polarizing Effects of Algorithmic Transparency

by   Aaron Springer, et al.

The rise of machine learning has brought closer scrutiny to intelligent systems, leading to calls for greater transparency and explainable algorithms. We explore the effects of transparency on user perceptions of a working intelligent system for emotion detection. In exploratory Study 1, we observed paradoxical effects of transparency which improves perceptions of system accuracy for some participants while reducing accuracy perceptions for others. In Study 2, we test this observation using mixed methods, showing that the apparent transparency paradox can be explained by a mismatch between participant expectations and system predictions. We qualitatively examine this process, indicating that transparency can undermine user confidence by causing users to fixate on flaws when they already have a model of system operation. In contrast transparency helps if users lack such a model. Finally, we revisit the notion of transparency and suggest design considerations for building safe and successful machine learning systems based on our insights.


page 4

page 8


What Are You Hiding? Algorithmic Transparency and User Perceptions

Extensive recent media focus has been directed towards the dark side of ...

Progressive Disclosure: Designing for Effective Transparency

As we increasingly delegate important decisions to intelligent systems, ...

Good governance and national information transparency: A comparative study of 117 countries

Information transparency is a major building block of responsible govern...

DECoVaC: Design of Experiments with Controlled Variability Components

Reproducible research in Machine Learning has seen a salutary abundance ...

Best Practices for Transparency in Machine Generated Personalization

Machine generated personalization is increasingly used in online systems...

Margin-distancing for safe model explanation

The growing use of machine learning models in consequential settings has...

Quantifying Transparency of Machine Learning Systems through Analysis of Contributions

Increased adoption and deployment of machine learning (ML) models into b...