• Home
  • Study Details
Not currently enrolling

Unintuitive Features Study

Nowadays, AI systems have been applied widely in a variety of predictive tasks, from objective detection to text classification. These AI systems have greatly advanced automated decision-making. However, sometimes humans and AI systems think in very different ways, which means humans and AI systems might use different evidence to make predictions. In this study, we are using sentiment analysis of Amazon product reviews as a case study. Humans will judge sentiments of different words with different AI explanations. Human and AI judgments will be compared to find to which extend human and AI knowledge align.

Age & Gender

  • 18 years ~ 99 years
  • Male, Female, Gender Inclusive

Contact the Team

Location

Thank you for your interest, but this study is not currently enrolling.

United States (Nationwide)

Additional Study Information

Principal Investigator

Yue Wang
School of Information and Library Science

Study Type

Behavioral or Social
Observational

Study Topics

Healthy Volunteer or General Population

IRB Number

23-1026

Research for Me logo

Copyright © 2013-2022 The NC TraCS Institute, the integrated home of the NIH Clinical and Translational Science Awards (CTSA) Program at UNC-CH.  This website is made possible by CTSA Grant UL1TR002489 and the National Center for Advancing Translational Sciences.

Questions?

  • This email address is being protected from spambots. You need JavaScript enabled to view it.
logo for the North Carolina Translational and Clinical Sciences Institute
logo for UNC Health
logo for UNC School of Medicine
logo for UNC Research