BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Phoenix
X-LIC-LOCATION:America/Phoenix
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19700101T000000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20241014T203101Z
LOCATION:Flagstaff
DTSTART;TZID=America/Phoenix:20240910T133000
DTEND;TZID=America/Phoenix:20240910T135000
UID:HFESAM_ASPIRE - Presented by HFES_sess142_LECT269@linklings.com
SUMMARY:Predicting Trust Dynamics with Personal Characteristics
DESCRIPTION:Lecture\n\nHyesun Chung and X. Jessie Yang (University of Mich
 igan)\n\nPrevious research into trust dynamics in human-autonomy interacti
 on has demonstrated that individuals exhibit specific patterns of trust wh
 en interacting repeatedly with automated systems. Moreover, people with di
 fferent types of trust dynamics have been shown to differ across seven per
 sonal characteristic dimensions: masculinity, positive affect, extraversio
 n, neuroticism, intellect, performance expectancy, and high expectations. 
 In this study, we develop classification models aimed at predicting an ind
 ividual's trust dynamics type--categorized as Bayesian decision-maker, dis
 believer, or oscillator--based on these key dimensions.  We employed multi
 ple classification algorithms including the random forest classifier, Supp
 ort Vector Machine, XGBoost, multinomial logistic regression, and Naive Ba
 yes, and conducted a comparative evaluation of their performance. The resu
 lts indicate that personal characteristics can effectively predict the typ
 e of trust dynamics, achieving an accuracy rate of 73.1%, and a weighted a
 verage F1 score of 0.64. This study underscores the predictive power of pe
 rsonal traits in the context of human-autonomy interaction.\n\nTrack: Huma
 n AI Robot Teaming (AI)\n\nSession Chair: Jade Driggs (Wichita State Unive
 rsity)
END:VEVENT
END:VCALENDAR