Massive Open Online Courses (MOOCs) have gradually become a dominant trend in education. Since 2014, the Ministry of Education in Taiwan has been promoting MOOC programs, with successful results. The ability of students to work at their own pace, however, is associated with low MOOC completion rates and has recently become a focus. The development of a mechanism to effectively improve course completion rates continues to be of great interest to both teachers and researchers. This study established a series of learning behaviors using the video clickstream records of students, through a MOOC platform, to identify seven types of cognitive participation models of learners. We subsequently built practical machine learning models by using K-nearest neighbor (KNN), support vector machines (SVM), and artificial neural network (ANN) algorithms to predict students’ learning outcomes via their learning behaviors. The ANN machine learning method had the highest prediction accuracy. Based on the prediction results, we saw a correlation between video viewing behavior and learning outcomes. This could allow teachers to help students needing extra support successfully pass the course. To further improve our method, we classified the course videos based on their content. There were three video categories: theoretical, experimental, and analytic. Different prediction models were built for each of these three video types and their combinations. We performed the accuracy verification; our experimental results showed that we could use only theoretical and experimental video data, instead of all three types of data, to generate prediction models without significant differences in prediction accuracy. In addition to data reduction in model generation, this could help teachers evaluate the effectiveness of course videos.
Sequential pattern mining has become more and more popular in recent years due to its wide applications and the fact that it can find more information than association rules. Two famous algorithms in sequential pattern mining are AprioriAll and PrefixSpan. These two algorithms not only need to scan a database or projected-databases many times, but also require setting a minimal support threshold to prune infrequent data to obtain useful sequential patterns efficiently. In addition, they must rescan the database if new items or sequences are added. In this paper, we propose a novel algorithm called Efficient Sequential Pattern Enumeration (ESPE) to solve the above problems. In addition, our method can be applied in many applications, such as for the itemsets appearing at the same time in a sequence. In our experiments, we show that the performance of ESPE is better than the other two methods using various datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.