CLEF NewsREEL 2017 Overview: Offline and Online Evaluation of Stream-based News Recommender Systems

Benjamin Kille, Andreas Lommatzsch, Frank Hopfgartner, Martha Larson, Torben Brodt

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

47 Downloads (Pure)

Abstract

The CLEF NewsREEL challenge allows researchers to evaluate news recommendation algorithms both online (NewsREEL Live) and offline (News-REEL Replay). Compared with the previous year NewsREEL challenged participants with a higher volume of messages and new news portals. In the 2017 edition of the CLEF NewsREEL challenge a wide variety of new approaches have been implemented ranging from the use of existing machine learning frameworks, to ensemble methods to the use of deep neural networks. This paper gives an
overview over the implemented approaches and discusses the evaluation results. In addition, the main results of Living Lab and the Replay task are explaine
Original languageEnglish
Title of host publicationCLEF 2017 Working Notes
Subtitle of host publicationConference and Labs of the Evaluation Forum
EditorsLinda Cappellato, Nicola Ferro, Lorraine Goeuriot, Thomas Mandl
PublisherCEUR
Pages1-13
Number of pages13
Publication statusPublished - 2017
EventCLEF 2017 - Conference and Labs of the Evaluation Forum: Information Access Evaluation meets Multilinguality, Multimodality, amd Visualization - Dublin, Ireland
Duration: 11 Sep 201714 Sep 2017
Conference number: 8
http://clef2017.clef-initiative.eu/

Publication series

NameCEUR Workshop Proceedings
PublisherCEUR
Volume1866
ISSN (Electronic)1613-0073

Conference

ConferenceCLEF 2017 - Conference and Labs of the Evaluation Forum
CountryIreland
CityDublin
Period11/09/1714/09/17
Internet address

Keywords

  • recommender systems
  • news
  • multi-dimensional evaluation
  • living lab
  • stream-based recommender

Fingerprint Dive into the research topics of 'CLEF NewsREEL 2017 Overview: Offline and Online Evaluation of Stream-based News Recommender Systems'. Together they form a unique fingerprint.

Cite this