Issue No. 01 - Jan.-March (2012 vol. 5)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TLT.2011.22
M. Mukunoki , Acad. Center for Comput. & Media Studies, Kyoto Univ., Kyoto, Japan
N. Pattanasri , Dept. of Social Inf., Kyoto Univ., Kyoto, Japan
M. Minoh , Acad. Center for Comput. & Media Studies, Kyoto Univ., Kyoto, Japan
Comprehension assessment is an essential tool in classroom learning. However, the judgment often relies on experience of an instructor who makes observation of students' behavior during the lessons. We argue that students should report their own comprehension explicitly in a classroom. With students' comprehension made available at the slide level, we apply a machine learning technique to classify presentation slides according to comprehension levels. Our experimental result suggests that presentation-based features are as predictive as bag-of-words feature vector which is proved successful in text classification tasks. Our analysis on presentation-based features reveals possible causes of poor lecture comprehension.
support vector machines, educational administrative data processing, learning (artificial intelligence), pattern classification, psychology, poor lecture comprehension, slide comprehension estimation, support vector machine, comprehension assessment, classroom learning, student comprehension, machine learning technique, presentation slide classification, comprehension level, presentation-based features, bag-of-words feature vector, text classification, Support vector machines, Machine learning, Materials, Training, Accuracy, Kernel, Feature extraction, SVM., Lecture analytics, lecture comprehension, learning skills
M. Mukunoki, N. Pattanasri, M. Minoh, "Learning to Estimate Slide Comprehension in Classrooms with Support Vector Machines", IEEE Transactions on Learning Technologies, vol. 5, no. , pp. 52-61, Jan.-March 2012, doi:10.1109/TLT.2011.22