Intelligent systems, which are on their way to becoming mainstream in everyday products, make recommendations and decisions for users based on complex computations. Researchers and policy makers increasingly raise concerns regarding the lack of transparency and comprehensibility of these computations from a user's perspective. Our aim is to advance existing UI guidelines for more transparency in complex real-world design scenarios involving multiple stakeholders. To this end, we contribute a stage-based process for designing transparent interfaces incorporating perspectives of users, designers, and providers, which we developed and validated with a commercial intelligent fitness coach. We further suggest exemplary participatory methods for this process to facilitate its application. With our work, we hope to provide guidance to practitioners and to pave the way for more transparency in intelligent systems.

Quick Actions

Share

Share this page

ios_share

https://hci.top/en/papers/iui/3669/2018

AdRecommended

Learn AI Coding at CodeNow

At a Glance

Paper Snapshot

fact_check
dataset
Source
IUI
calendar_month
Year
2018
emoji_events
Award
No award tagged
group
Authors
6 authors
sell
Subtopics
Explainable AI (XAI), Algorithmic Transparency & Auditability, Privacy by Design & User Control
work
Professions
UI/UX Designers, Privacy Policy Makers
article
Content Status
Abstract only
hub
Related Papers
1 related papers