Abstract

With the ubiquitous access to the internet, news portals have become heavily consumed online services. The huge amount of published news makes it difficult for users to find relevant articles. Recommender systems have been developed for supporting users in finding the most interesting items in vast collections of available news. In contrast to traditional recommender systems, news recommender systems must address additional challenges. These challenges include the continuous changes in the set of items and the highly contextually dependent relevance of items as well as tight time constraints for providing recommendations and scalability requirements. In this work, we present our recommender system built based on Apache Mahout tailored to the needs of news recommender systems. Two algorithms are combined to ensure highly precise recommendations and a high reliability. The system is evaluated in the CLEF NewsREEL challenge. We discuss the performance of different tested algorithms and configurations. The evaluation shows that the developed system provides high quality results and fulfills the requirements of stream-based recommender scenarios.

@inproceedings{BeckEtAl:ANewsRecommenderSystemBasedOnApacheMahout,
author = {Paul Beck and Manuel Blaser and Adrian Michalke and Andreas Lommatzsch},
title = {A System for Online News Recommendations in Real-Time with Apache Mahout},
booktitle = {{Working Notes of the 8th International Conference of the CLEF Initiative}},
year = {2017},
location = {Dublin, Ireland},
numpages = {15},
issn = {1613-0073},
volume={1866},
publisher = {CEUR Workshop Proceedings},
note = {http://ceur-ws.org/Vol-1866/paper_164.pdf},
keywords={recommender system, news recommender, stream processing, algorithms, similarity metrics, scalability}
}