FoL 2026
AIED

An Item Response Theory Model for Addressing Halo Effects in Performance Assessment

Thu Jul 2, 2:25 PM–2:50 PM · North 205
★ Notable speakers
Masaki Uto — Item response theory for automated essay scoring; Bayesian psychometrics; multidimensional IRT; neural AES

Presents an IRT model that accounts for halo effects—raters' tendency to let overall impressions bias scores—in performance-based assessment.

Authors

Masaki Uto, Ryota Kitakaze