Andre Paulino de Lima

Andre Paulino de Lima, Paula Castro, Suzana Carvalho Vaz de Andrade et al.

There are challenges that must be overcome to make recommender systems useful in healthcare settings. The reasons are varied: the lack of publicly available clinical data, the difficulty that users may have in understanding the reasons why a recommendation was made, the risks that may be involved in following that recommendation, and the uncertainty about its effectiveness. In this work, we address these challenges with a recommendation model that leverages the structure of psychometric data to provide visual explanations that are faithful to the model and interpretable by care professionals. We focus on a narrow healthcare niche, gerontological primary care, to show that the proposed recommendation model can assist the attending professional in the creation of personalised care plans. We report results of a comparative offline performance evaluation of the proposed model on healthcare datasets that were collected by research partners in Brazil, as well as the results of a user study that evaluates the interpretability of the visual explanations the model generates. The results suggest that the proposed model can advance the application of recommender systems in this healthcare niche, which is expected to grow in demand , opportunities, and information technology needs as demographic changes become more pronounced.

Andre Paulino de Lima, Sarajane Marques Peres

In this study, we address the challenge of measuring the ability of a recommender system to make surprising recommendations. Although current evaluation methods make it possible to determine if two algorithms can make recommendations with a significant difference in their average surprise measure, it could be of interest to our community to know how competent an algorithm is at embedding surprise in its recommendations, without having to resort to making a direct comparison with another algorithm. We argue that a) surprise is a finite resource in a recommender system, b) there is a limit to how much surprise any algorithm can embed in a recommendation, and c) this limit can provide us with a scale against which the performance of any algorithm can be measured. By exploring these ideas, it is possible to define the concepts of maximum and minimum potential surprise and design a surprise metric called "normalised surprise" that employs these limits to potential surprise. Two experiments were conducted to test the proposed metric. The aim of the first was to validate the quality of the estimates of minimum and maximum potential surprise produced by a greedy algorithm. The purpose of the second experiment was to analyse the behaviour of the proposed metric using the MovieLens dataset. The results confirmed the behaviour that was expected, and showed that the proposed surprise metric is both effective and consistent for differing choices of recommendation algorithms, data representations and distance functions.