Evaluation Perspectives of Recommender Systems: Driving Research and Education: Report from Dagstuhl Seminar 24211

Christine Bauer* (Publisher), Alan Said* (Publisher), Eva Zangerle* (Publisher), Neil Hurley, Bart Goethals, Robin Burke, Jürgen Ziegler, Michael Ekstrand, Joseph Konstan, Martijn C. Willemsen, Joeran Beel, Vito Walter Anelli, Alejandro Bellogin, Oliver Jeunen, Lien Michiels, Denis Parra , Rodrygo L. T. Santos, Alexander Tuzhilin

*Corresponding author for this work

Research output: Book/Report/Legal commentaryResearch report

Abstract

This report documents the program and the outcomes of Dagstuhl Seminar 24211, "Evaluation Perspectives of Recommender Systems: Driving Research and Education", which brought together 41 participants from 16 countries. The seminar brought together distinguished researchers and practitioners from the recommender systems community, representing a range of expertise and perspectives. The primary objective was to address current challenges and advance the ongoing discourse on the evaluation of recommender systems. The participants' diverse backgrounds and perspectives on evaluation significantly contributed to the discourse on this subject. The seminar featured eight presentations on current challenges in the evaluation of recommender systems. These presentations sparked the general discussion and facilitated the formation of groups around these topics. As a result, five working groups were established, each focusing on the following areas: theory of evaluation, fairness evaluation, best-practices for offline evaluations of recommender systems, multistakeholder and multimethod evaluation, and evaluating the long-term impact of recommender systems.
Original languageEnglish
Place of PublicationLeibniz
Number of pages115
Volume14
Edition5
DOIs
Publication statusPublished - 26 Nov 2024
EventDagstuhl Seminar 24211: Evaluation Perspectives of Recommender Systems: Driving Research and Education - Schloss Dagstuhl, Wadern, Germany
Duration: 20 May 202424 May 2024
https://www.dagstuhl.de/24211

Publication series

NameDagstuhl Reports
PublisherSchloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing
No.5
Volume14
ISSN (Print)2192-5283

Keywords

  • evaluation
  • recommender systems
  • information retrieval
  • user interaction
  • intelligent systems
  • fairnessrecommender systemsevaluationinformation retrievaluser interactionintelligent systems

Fields of Science and Technology Classification 2012

  • 102 Computer Sciences
  • 509 Other Social Sciences

Cite this