An Identification of Learners' Confusion through Language and Discourse Analysis.

摘要: The substantial growth of online learning, in particular, Massively Open Online Courses (MOOCs), supports research into the development better models for effective learning. Learner 'confusion' is among one identified aspects which impacts overall learning process, and ultimately, course attrition. Confusion a learner an individual state bewilderment uncertainty how to move forward. majority recent works neglect 'individual' factor measure influence community-related (e.g. votes, views) confusion classification. While this useful measure, as popularity one's post can indicate that many other students have similar regarding topics, these personalised context, such individual's affect or emotions. Certain physiological facial expressions, heart rate) been utilised classify small medium classrooms. However, techniques are challenging adopt MOOCs. To bridge gap, we propose approach solely based on language discourse learners, outperforms previous models. We contribute through novel linguistic feature set predictive train classifier using domain, successfully applying it across domains.