Self-regulated Learning

From Penn Center for Learning Analytics Wiki
Jump to navigation Jump to search

Zhang et al. (in press) [1]

  • Four detectors (i.e., numerical representation, contextual representation, outcome orientation, and data transformation) relating to two cognitive operations (assembling and translating) were built to detect middle school students' use of self-regulated learning in mathematical problem-solving process.
  • Detectors were built using XGBoost with labels coded from text replays and features distilled from log data and textual responses.
  • In each detector, relatively small differences in AUC were observed across gender and racial/ethnic groups, and no student group (either gender or racial/ethnic group) consistently had the best-performing detectors