I have launched a website CourseMiner for open courses mining, which used simple text mining methods like tag extraction (keyword or keyphrase extraction) and document similarity or text similarity computing. Till now it just add Coursera and edX platform, and will add other open course platform crawlers.

For keyword extraction, you can “Getting Started with Keyword Extraction“. For document similarity, CourseMiner now used the topic model method to compute the similarity between the courses.

CourseMiner is very simple now, but we want mining course for the World.