Visualizing Serendipitous Recommendations in User Controlled Recommender System for Learning

Abstract

In this paper, we report on a preliminary study about user preferences for recommender system visualizing serendipitous recommendations. A focus group study of fifty nine users (students) was studied for recording their preferences. The focus group was shown and explained the interaction with six(6) common recommender system visualization techniques. Multivariate analysis and LDA ( Linear Discriminant Analysis) and Clustering were performed to compute various visualization significance against various recommender systems attributes. The results showed there is difference in various types of recommender visualization when presenting/generating recommender results facilitating serendipity. This research enables software engineers and data scientist to design visualizations for recommender systems that focus users that need serendipitous recommendations presentation along with accuracy