EB-NeRD comprises data from over 1 million unique users, with more than 37 million impression logs and over 251 million interactions from Ekstra Bladet. Alongside, we offer a collection of more than 125,000 news articles, enriched with textual content features such …

The Ekstra Bladet News Recommendation Dataset (EB-NeRD) was created to support advancements in news recommendation research. It was collected from user behavior logs at Ekstra Bladet . We collected behavior logs from active users during the 6 …

ekstrabladet.dk •The common news flow is supplemented with recommenders at all horizontal placements. •Creates a broader news flow because the recommenders supplement with relevant content for the individual. •The systems have increased free traffic (+110%), use of paid content (+38%), and sales of subs (+35%) at the horizontal placements.

The Ekstra Bladet News Recommendation Dataset (EB-NeRD) is a large-scale Danish dataset created by Ekstra Bladet to support ad- vancements and benchmarking in news recommendation research.

The dataset for the ACM RecSys Challenge 2024, named EB-NeRD, is a large-scale Danish dataset created by Ekstra Bladet to support advancements and benchmarking in News Recommendation re-search. EB-NeRD includes data from over 2.3 million users and more than 380 million impression logs collected from Ekstra Bladet.

EB-NeRD dataset. This paper presents the solution developed by team “:D”, which secured the first place in the challenge. Our ap-proach combines Transformers, Gradient Boosting Decision Trees (GBDT), and ensemble techniques in a three-stage recommendation pipeline. We introduce time-aware feature engineering methods

resources, please refer to the oRicial website recsys.eb.dk (“Website”). 2. Eligibility To ensure fair competition and compliance with legal and ethical standards, the following eligibility criteria apply to all participants in the Challenge: a. Conflict of Interest:

(EB-NeRD), a comprehensive Danish dataset specifically designed for advancing news recommendation research. This dataset, pro-vided by Ekstra Bladet for the RecSys Challenge 2024, offers a rich source of information for developing and …

ekstrabladet.dk during a period of 6 weeks. The Dataset is made available in a machine-readable format and includes relevant metadata from the articles read during the period as well as the articles’ titles, subtitles, and body text. The Dataset does not include photos and bylines.

Large Scale Hierarchical User Interest Modeling for Click-through Rate Prediction RecSys Challenge ’24, October 14–18, 2024, Bari, Italy Figure 2: We utilize the multimodal representations along with the side information of items to distill the long-standing