RECOMMENDATION SYSTEMS IN MOOCS
Distance learning, where students take courses while being physically separated from their teachers for majority of the duration of the course is by no means a new phenomenon. It has been delivered through mail, radio and TV and recently through the Internet. Distance learning provides limited interaction between students and lectures and rarely any collaboration among the students themselves. Which approach we will use to solve this problem? We will base our work upon MOOCs, which offers openly online courses, for free, to students anywhere in the world.
Recommendation systems changed the way inanimate websites communicate with their users. Rather than providing a static experience in which users search for, recommender systems increase interaction to provide a richer experience. Recommender systems identify recommendations autonomously for individual users based on past purchases and searches, and on other users' behavior. This article will introduce recommender systems and the algorithms that we will implement in a MOOC platform.
Many algorithms and an even larger set of variations of those algorithms exist for recommendation engines. Some that have been used successfully include:
- Bayesian Belief Nets, which can be visualized as a directed acyclic graph, with arcs representing the associated probabilities among the variables.
- Markov chains, which take a similar approach to Bayesian Belief Nets but treat the recommendation problem as sequential optimization instead of simply prediction.
- Rocchio classification (developed with the Vector Space Model), which exploits feedback of the item relevance to improve recommendation accuracy.
As we have already stated this paper will present how recommendation systems can improve the quality of education in the MOOC.