Teaching Recommender in Python

Recommender systems in education are used to support the teaching-learning processes. These systems could make easier to take advantage of the social knowledge in competence-based and blended courses. In this paper we propose a system that merges collaborative-based and knowledge-based filtering techniques in order to recommend activities and resources, aiming to support the students to achieve the expected competence levels. The system takes into account the experiences stored and rated by students who have taken the course before (social knowledge), and the competence levels achieved by a student in the same current course. This information is analyzed against the competence levels achieved by former students, then the systems retrieve personalized recommendations to the current student, according to the available information of former students with similar performance. Our findings suggest that the technical approach is correct. They reflect that the social knowledge and the learning results are good sources of valuable recommendations.