A Novel Classification Framework for Evaluating Individual and Aggregate Diversity in Top-N Recommendations

Abstract

The primary goal of a recommender system is to generate high quality user-centred recommendations. However, the traditional evaluation methods and metrics were developed before researchers understood all the factors that increase user satisfaction. This study is an introduction to a novel user and item classification framework. It is proposed that this framework should be used during user-centred evaluation of recommender systems and the need for this framework is justified through experiments. User profiles are constructed and matched against other users’ profiles to formulate neighbourhoods and generate top-N recommendations. The recommendations are evaluated to measure the success of the process. In conjunction with the framework, a new diversity metric is presented and explained. The accuracy, coverage, and diversity of top-N recommendations is illustrated and discussed for groups of users. It is found that in contradiction to common assumptions, not all users suffer as expected from the data sparsity problem. In fact, the group of users that receive the most accurate recommendations do not belong to the least sparse area of the dataset.