BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME: Empirical Studies on the Impact of Visualization Design on Hu
 man Cognition\, Judgment\, and AI Understanding
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260807T194307Z
UID:tag:localist.com\,2008:EventInstance_51081654989974
DTSTART:20251111T150000Z
DTEND:20251111T160000Z
DESCRIPTION:Candidate Name: Milad Rogha\nProgram: Computer Science​​​
 ​​​​\nCommittee Chairs: Dr. Wenwen Dou​​​​​​​\nCommi
 ttee Members: Dr. Depeng Xu\, Dr. Doug Markant\, Dr. George Banks\nAbstrac
 t:\n\nThe growing importance of machine learning and large language models
  in decision-making across various domains\, including healthcare and law\
 , underscores the necessity of effectively and responsibly communicating t
 heir performance to avoid misinterpretation and overreliance. This dissert
 ation explores how visualization design and contextual framing impact huma
 n understanding\, confidence\, and decision-making in AI-assisted environm
 ents through three empirical studies.\n\nThree user experiments collective
 ly investigate this challenge. The first explores how eliciting prior beli
 efs and presenting contrasting narratives affect engagement\, recall\, and
  attitude change toward data-driven news articles. The second investigates
  how the source and presence of AI-generated recommendations shape decisio
 n-making in content moderation\, revealing a trade-off between decision sp
 eed and confidence. The third evaluates how alternative confusion matrix v
 isualizations\, such as frequency-framed and Sankey designs\, affect lay u
 sers’ comprehension and their confidence in calibrating AI model perform
 ance.\n\nTogether\, these studies contribute to a deeper understanding of 
 how visualization design and contextual framing shape user cognition and b
 ehavior in AI-supported environments. These studies show that well-designe
 d visualizations can meaningfully enhance non-experts’ ability to unders
 tand and appropriately use AI systems. The findings offer practical recomm
 endations for creating more accessible\, transparent\, and responsible hum
 an-AI interactions by supporting informed and calibrated decision-making a
 mong lay users.
LOCATION:Register through this form to receive Zoom link: http://bit.ly/3L2
 dE5U
SUMMARY: Empirical Studies on the Impact of Visualization Design on Human C
 ognition\, Judgment\, and AI Understanding
URL;VALUE=URI:https://campusevents.charlotte.edu/event/Empirical-Studies-on
 -the-Impact-of-Visualization-Design-on-Human-Cognition-Judgment-and-AI-Und
 erstanding
CATEGORIES:Academic Calendar
CATEGORIES:Public
END:VEVENT
END:VCALENDAR