RecSys Challenge 2024: Balancing Accuracy and Editorial Values in News Recommendation

Johannes Kruse; Kasper Lindskow; Saikishore Kalloori; Marco Polignano; Claudio Pomo; Abhishek Srivastava; Anshuk Uppal; Michael Riis Andersen; Jes Frellsen

doi:10.1145/3640457.3687164

RecSys Challenge 2024: Balancing Accuracy and Editorial Values in News Recommendation

Johannes Kruse
, Kasper Lindskow
, Saikishore Kalloori
, Marco Polignano
, Claudio Pomo
, Abhishek Srivastava
, Anshuk Uppal
, Michael Riis Andersen
, Jes Frellsen

Politiken
Swiss Federal Institute of Technology Zurich
Università degli Studi di Bari Aldo Moro
Polytechnic University of Bari
Indian Institute of Management Visakhapatnam

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

Abstract

The RecSys Challenge 2024 aims to advance news recommendation by addressing both the technical and normative challenges inherent in designing effective and responsible recommender systems for news publishing. This paper describes the challenge, including its objectives, problem setting, and the dataset provided by the Danish news publishers Ekstra Bladet and JP/Politikens Media Group ("Ekstra Bladet"). The challenge explores the unique aspects of news recommendation, such as modeling user preferences based on behavior, accounting for the influence of the news agenda on user interests, and managing the rapid decay of news items. Additionally, the challenge embraces normative complexities, investigating the effects of recommender systems on news flow and their alignment with editorial values. We summarize the challenge setup, dataset characteristics, and evaluation metrics. Finally, we announce the winners and highlight their contributions. The dataset is available at: https://recsys.eb.dk.

Original language	English
Title of host publication	Proceedings of the RecSys '24: 18th ACM Conference on Recommender Systems
Publisher	Association for Computing Machinery
Publication date	2024
Pages	1195-1199
ISBN (Electronic)	979-8-4007-0505-2/24/10
DOIs	https://doi.org/10.1145/3640457.3687164
Publication status	Published - 2024
Event	18th ACM Conference on Recommender Systems (RecSys ’24) - Bari, Italy Duration: 14 Oct 2024 → 18 Oct 2024

Conference

Conference	18th ACM Conference on Recommender Systems (RecSys ’24)
Country/Territory	Italy
City	Bari
Period	14/10/2024 → 18/10/2024

Keywords

Recommender Systems
Competition
News Recommendations
Dataset
Beyond-Accuracy
Editorial Values

Access to Document

10.1145/3640457.3687164

OpenUrl availability

Check availability in DTU Findit

Cite this

Kruse, J., Lindskow, K., Kalloori, S., Polignano, M., Pomo, C., Srivastava, A., Uppal, A., Andersen, M. R., & Frellsen, J. (2024). RecSys Challenge 2024: Balancing Accuracy and Editorial Values in News Recommendation. In Proceedings of the RecSys '24: 18th ACM Conference on Recommender Systems (pp. 1195-1199). Association for Computing Machinery. https://doi.org/10.1145/3640457.3687164

@inproceedings{fe4413a903e54da5bc79245c9013a1db,

title = "RecSys Challenge 2024: Balancing Accuracy and Editorial Values in News Recommendation",

abstract = "The RecSys Challenge 2024 aims to advance news recommendation by addressing both the technical and normative challenges inherent in designing effective and responsible recommender systems for news publishing. This paper describes the challenge, including its objectives, problem setting, and the dataset provided by the Danish news publishers Ekstra Bladet and JP/Politikens Media Group ({"}Ekstra Bladet{"}). The challenge explores the unique aspects of news recommendation, such as modeling user preferences based on behavior, accounting for the influence of the news agenda on user interests, and managing the rapid decay of news items. Additionally, the challenge embraces normative complexities, investigating the effects of recommender systems on news flow and their alignment with editorial values. We summarize the challenge setup, dataset characteristics, and evaluation metrics. Finally, we announce the winners and highlight their contributions. The dataset is available at: https://recsys.eb.dk.",

keywords = "Recommender Systems, Competition, News Recommendations, Dataset, Beyond-Accuracy, Editorial Values",

author = "Johannes Kruse and Kasper Lindskow and Saikishore Kalloori and Marco Polignano and Claudio Pomo and Abhishek Srivastava and Anshuk Uppal and Andersen, \{Michael Riis\} and Jes Frellsen",

year = "2024",

doi = "10.1145/3640457.3687164",

language = "English",

pages = "1195--1199",

booktitle = "Proceedings of the RecSys '24: 18th ACM Conference on Recommender Systems",

publisher = "Association for Computing Machinery",

address = "United States",

note = "18th ACM Conference on Recommender Systems (RecSys {\textquoteright}24) ; Conference date: 14-10-2024 Through 18-10-2024",

}

Kruse, J, Lindskow, K, Kalloori, S, Polignano, M, Pomo, C, Srivastava, A, Uppal, A, Andersen, MR & Frellsen, J 2024, RecSys Challenge 2024: Balancing Accuracy and Editorial Values in News Recommendation. in Proceedings of the RecSys '24: 18th ACM Conference on Recommender Systems. Association for Computing Machinery, pp. 1195-1199, 18th ACM Conference on Recommender Systems (RecSys ’24), Bari, Italy, 14/10/2024. https://doi.org/10.1145/3640457.3687164

RecSys Challenge 2024: Balancing Accuracy and Editorial Values in News Recommendation. / Kruse, Johannes; Lindskow, Kasper; Kalloori, Saikishore et al.
Proceedings of the RecSys '24: 18th ACM Conference on Recommender Systems. Association for Computing Machinery, 2024. p. 1195-1199.

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - RecSys Challenge 2024: Balancing Accuracy and Editorial Values in News Recommendation

AU - Kruse, Johannes

AU - Lindskow, Kasper

AU - Kalloori, Saikishore

AU - Polignano, Marco

AU - Pomo, Claudio

AU - Srivastava, Abhishek

AU - Uppal, Anshuk

AU - Andersen, Michael Riis

AU - Frellsen, Jes

PY - 2024

Y1 - 2024

N2 - The RecSys Challenge 2024 aims to advance news recommendation by addressing both the technical and normative challenges inherent in designing effective and responsible recommender systems for news publishing. This paper describes the challenge, including its objectives, problem setting, and the dataset provided by the Danish news publishers Ekstra Bladet and JP/Politikens Media Group ("Ekstra Bladet"). The challenge explores the unique aspects of news recommendation, such as modeling user preferences based on behavior, accounting for the influence of the news agenda on user interests, and managing the rapid decay of news items. Additionally, the challenge embraces normative complexities, investigating the effects of recommender systems on news flow and their alignment with editorial values. We summarize the challenge setup, dataset characteristics, and evaluation metrics. Finally, we announce the winners and highlight their contributions. The dataset is available at: https://recsys.eb.dk.

AB - The RecSys Challenge 2024 aims to advance news recommendation by addressing both the technical and normative challenges inherent in designing effective and responsible recommender systems for news publishing. This paper describes the challenge, including its objectives, problem setting, and the dataset provided by the Danish news publishers Ekstra Bladet and JP/Politikens Media Group ("Ekstra Bladet"). The challenge explores the unique aspects of news recommendation, such as modeling user preferences based on behavior, accounting for the influence of the news agenda on user interests, and managing the rapid decay of news items. Additionally, the challenge embraces normative complexities, investigating the effects of recommender systems on news flow and their alignment with editorial values. We summarize the challenge setup, dataset characteristics, and evaluation metrics. Finally, we announce the winners and highlight their contributions. The dataset is available at: https://recsys.eb.dk.

KW - Recommender Systems

KW - Competition

KW - News Recommendations

KW - Dataset

KW - Beyond-Accuracy

KW - Editorial Values

U2 - 10.1145/3640457.3687164

DO - 10.1145/3640457.3687164

M3 - Article in proceedings

SP - 1195

EP - 1199

BT - Proceedings of the RecSys '24: 18th ACM Conference on Recommender Systems

PB - Association for Computing Machinery

T2 - 18th ACM Conference on Recommender Systems (RecSys ’24)

Y2 - 14 October 2024 through 18 October 2024

ER -

RecSys Challenge 2024: Balancing Accuracy and Editorial Values in News Recommendation

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this