Abstract
Machine-learning (ML) enabled products and features allow for an expanded set of user inputs and system outputs. In the case of consumer-facing ML-enabled products, examples of this include the ability to take natural language as an input, or to generate personalized feeds or recommendations (system output) based on the behavior of a user. Based on our experience conducting UX research on ML-enabled products, we propose that this expanded set of inputs and outputs requires that we modify our usual methodologies in a few ways, depending on the product & research objectives. Specifically, we propose that researching ML- enabled products may require 1) more time for the user to explore or experiment with the product 2) talking to more user types and/or 3) more comprehensive prototypes or presentation of the product concept. To flesh this framework out, we present three examples of ML-enabled products we tested in the past few years and the methodological modifications required.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: Proceedings of the Human Factors and Ergonomics Society Annual Meeting
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.