Abstract
With the popularity of MOOCs (Massive Open Online Courses), massive structured, semi-structured and unstructured data about learning is recorded for further analysis and applications. Forum is the direct way for learners to ask questions and clarify their misconceptions. Therefore, we utilize the plain text of posts and responses in MOOCs forum to extract keywords of misconceptions for instructors based on Natural Language Processing (NLP) technique. In this study, the researchers mining these misconceptions from over 120 thousands of single Chinese words and 15 thousands of English words in a course. Moreover, we visualize them by word clouds and social network graphs for quickly and better understanding of misconceptions and their correlation.