User Control and Serendipitous Recommendations in Learning Environments
Ahmad Hassan Afridi · Procedia Computer Science · 2018
This paper reports about the study of serendipitous recommendations generation by recommender systems in educational environments. The recommender system provides students with serendipity slider to express desired serendipity and accuracy of recommendations. The recommender uses interface level processing of randomization of recommendations list. The increasing serendipity results in changing score/values of accuracy of recommendations. This was tested by deploying a study material recommender system based on collaborative filtering techniques. The recommender system was used by 60 students in a focus group setting. In conclusion, the research suggests that serendipitous recommendations can be archived using user controlled recommenders in learning environment.