Active learning driven by rating impact analysis

Abstract

Many works have been proposed in order to improve the recommendation accuracy. Algorithms aiming to improve recommendation accuracy have been developed and evaluated. These algorithms usually work with training data sets which are learned and used to make predictions on users' tastes. The training data set choice is a difficult task not only due to the technical nature of the algorithm used, but also because of the user issues associated with the acquisition of their opinions, since the training data consist of users' opinions. In this work we show the importance of understanding which predictions are impacted when a rating is acquired by developing a naive active learning criterion based on the number of impacted predictions. To do that, a Rating Impact Analysis method for the user-based collaborative filtering is proposed and applied to the active learning issue.