Engagement and Affect Detection

From Penn Center for Learning Analytics Wiki
Revision as of 06:09, 10 June 2022 by Ryan (talk | contribs) (added detail)
Jump to navigation Jump to search

Ocumpaugh et al. (2014) pdf

  • Models detecting student affective states (boredom, confusion, engaged concentration, frustration) from the interaction with ASSISTment system
  • Study involved urban, rural, and suburban learners
  • Detectors generally performed the best for the same subpopulation that they were trained on (average kappa = 0.26, A′ = 0.67), and worse for other subpopulations (average kappa = 0.03 and A′ = 0.52)
  • Detectors trained on combined population generally performed better for urban and suburban population (kappa = 0.18, 0.16; A′ = 0.62, 0.66) and not as well for rural population (kappa = 0.06; A′ = 0.54)