Reproduce “Progressive Disclosure: Designing for Effective Transparency” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Aaron Springer, Steve Whittaker
This research empirically investigates user reactions to algorithmic transparency in an emotional text analysis system, revealing that while users initially desire more detail, excessive transparency can be distracting and undermine trust, leading to the proposal of progressive disclosure as an effective design principle.
Key insights
- Users' anticipated preference for more detailed transparency often shifts after actual interaction, with many finding excessive real-time information distracting or overwhelming.
- Detailed transparency can paradoxically erode user trust by exposing minor algorithmic 'errors' or interpretations that conflict with users' common-sense 'folk theories,' even when the system is objectively correct.
- Less transparency can lead users to overattribute intelligence to a system, believing it considers complex context when it only relies on simpler features.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.