Building a Dataset for Personalized Learning Recommendation System

Abstract

In the last decade many researchers have developed recommendation systems (RSs) for technology enhanced learning (TEL) but only a few of them validated these RSs based on real time scenarios. Researchers raised the issue of missing datasets for RSs in TEL that can be used as benchmarks to compare different recommendation building approaches. Also, the availability of benchmark datasets helps in evaluating the recommendation algorithms and draw stronger conclusions about the effectiveness of such recommendation algorithms. In this paper, the issues of missing benchmark datasets for personalized recommendation systems that include social interaction through learner networks have been investigated. The paper proposes a methodology for building our own collaborative dataset via learning management systems (LMS) and educational repositories. This dataset will enhance student learning by recommending relevant learning materials from the former student's competence qualifications and also validate the proposed learning recommendation system. The planned dataset offer resources and information on the usage of more than 22,785 resources from 658 courses apart from data from social learner networks (blogs, wikis, chats and forums), which adds another 5,400 stored files in LMS database. Further, we also examined the challenges that exist in building and sharing such datasets which can be used by the TEL RSs community.