Context-aware recommendation systems in mobile environments

  1. María Mercedes Rodríguez Hernández
Supervised by:
  1. Sergio Ilarri Artigas Director

Defence university: Universidad de Zaragoza

Year of defence: 2017

  1. José Ramón Ríos Viqueira Chair
  2. Ramón Hermoso Traba Secretary
  3. Florence Sedes Committee member

Type: Thesis

Teseo: 521861 DIALNET


Nowadays, the huge amount of information available may easily overwhelm users when they need to take a decision that involves choosing among several options. As a solution to this problem, Recommendation Systems (RS) have emerged to offer relevant items to users. The main goal of these systems is to recommend certain items based on user preferences. Unfortunately, traditional recommendation systems do not consider the user’s context as an important dimension to ensure high-quality recommendations. Motivated by the need to incorporate contextual information during the recommendation process, Context-Aware Recommendation Systems (CARS) have emerged. However, these recent recommendation systems are not designed with mobile users in mind, where the context and the movements of the users and items may be important factors to consider when deciding which items should be recommended. Therefore, context-aware recommendation models should be able to effectively and efficiently exploit the dynamic context of the mobile user in order to offer her/him suitable recommendations and keep them up-to-date. The research area of this thesis belongs to the fields of context-aware recommendation systems and mobile computing. We focus on the following scientific problem: how could we facilitate the development of context-aware recommendation systems in mobile environments to provide users with relevant recommendations? This work is motivated by the lack of generic and flexible context-aware recommendation frameworks that consider aspects related to mobile users and mobile computing. In order to solve the identified problem, we pursue the following general goal: the design and implementation of a context-aware recommendation framework for mobile computing environments that facilitates the development of context-aware recommendation applications for mobile users. In the thesis, we contribute to bridge the gap not only between recommendation systems and context-aware computing, but also between CARS and mobile computing.