A hybrid recommendation system for news in a mobile environment

Abstract

Over the last few years consumption of news articles has shifted more and more from the written versions towards the web. Mobile devices, which became more powerful, with larger screens and connected to the Internet, have had a great influence on this paradigm change. A critical problem associated to online news is related to the fact that the large number of daily articles can be overwhelming to the users. Recommendation services can largely improve the efficiency and accuracy of acquired information. These systems are designed to filter critical news, key events and meaningful items that might be of interest to a reader. In this paper, a news recommendation system in a mobility scenario is presented. The implemented recommendation system combines content-based and georeferenced recommendation techniques. Recommendations are supported by short-term and long-term user profiles created implicitly and considering also the mobile device geolocation. The final recommendation list is obtained by combining recommendations provided by the different recommendation approaches. To evaluate the performance of the solution, a user study was conducted. Results indicate that the quality of the recommendations is acknowledged by the test users. The system was integrated in a mobile application of a Portuguese newspaper (Público) in the context of the project Pglobal. © 2016 ACM.