Padrões de design de interação para Sistemas de Recomendação.

Abstract

Recommender Systems are software tools that provide suggestions for items that may be useful to the user. These systems create a profile for storing usage data, which is used to indicate new products. Recommender Systems are present in virtual stores, streaming services, travel websites, among others. This dissertation aims to investigate and present interaction patterns for recommender systems. To achieve this goal the study was divided into three stages. In the first phase, a systematic review was carried out to identify research related to interaction elements of the recommender systems. Then, thirteen digital platforms were selected that adopt recommender systems and the Cognitive Walkthrough was carried out to map the interaction elements. With the collected data it was possible to elaborate interaction patterns that could help designers and developers in future projects of recommender systems.