Année : 2019
Lieu de publication de l'article :

Résumé de l'article

Massive Open Online Courses (MOOCs) often incorporate lecture-based learning along with lecture notes, textbooks, and videos tostudents. Moreover, MOOCs also incorporate practice activities andquizzes. Student learning in MOOCs can be tracked and improvedusing state-of-the-art student modeling. Currently, this means em-ploying conventional student models that are constructed aroundIntelligent Tutoring Systems (ITS). Traditional ITS systems onlyutilize students performance interactions (quiz, problem-solving orpractice activities). Therefore, text interactions are entirely ignoredwhile modeling students performance in MOOCs using these cog-nitive models. In this work, we propose a Comprehension FactorAnalysis model (CFM) for online courses, which integrates studentreading interactions in student models to track and predict learn-ing outcomes. Our model evaluation shows that CFM outperformsstate-of-the-art models in predicting students’ performance in aMOOC. These models can help better student-wise adaptation inthe context of MOOCs.KEYWORDSStudent modeling, Education Data Mining, MOOCs, Reading Be-haviourACM Reference Format:Khushboo Thaker, Paulo Carvalho, and Kenneth Koedinger. 2019. Com-prehension Factor Analysis: Modeling student’s reading behaviour: Ac-counting for reading practice in predicting students’ learning in MOOCs. InThe 9th International Learning Analytics & Knowledge Conference (LAK19),March 4–8, 2019, Tempe, AZ, USA. ACM, New York, NY, USA, 5 pages.https://doi.org/10.1145/3303772.33038171

Mots-clés

Massive open online course,Factor analysis,List comprehension,Interaction,Problem solving,Cognitive model,