Datasets for recommender systems are few and often inadequate for the contextualized nature of news recommendation. News recommender systems are both time-and location-dependent, make use of implicit signals, and often include both collaborative and content-based components. In this paper we introduce the Adressa compact news dataset, which supports all these aspects of news recommendation. The dataset comes in two versions, the large 20M dataset of 10 weeks' traffic on Adresseavisen's news portal, and the small 2M dataset of only one week's traffic. We explain the structure of the dataset and discuss how it can be used in advanced news recommender systems.

Recommender systems are built to provide the most proper item or information within the huge amount of data on the internet without the manual effort of the users. As a specific application domain, news recommender systems aim to give the most relevant news article recommendations to users according to their personal interests and preferences. News recommendation have specific challenges when compared to the other domains. From the technical point of view there are many different methods to build a recommender system. Thus, while general methods are used in news recommendation, researchers also need some new methods to make proper news recommendations. In this paper we present the different approaches to news recommender systems and the challenges of news recommendation.

Despite the fact that recommender systems are becoming increasingly popular in every aspect of the web, users might hesitate to use these personalization-based services in return of their personal information if they believe their privacy is compromised in any possible way. While new privacy regulations in Europe bring more transparency and control over data collection to users, this study aims to provide a better understanding of the users' perception over privacy in recommender systems domain over several aspects such as behavioral preferences, privacy preferences, trust, data ownership and control over own data through an on-line survey. The results indicate that the majority of the respondents consider that recommender systems violate user privacy in different ways. Further, the results indicate that increased control and perceived sense of ownership over one's own data may help to decrease the negative attitudes towards recommender systems and providers and to re-instate and increase users' trust. However, the findings also indicate that users' trust may be hard to re-establish in cases where the thought of "apparently"/in theory go hand in hand with more transparency and user control will in reality/in practice not lead to drastic changes.

No abstract

Abstract. News recommender systems provide users with access to news stories that they find interesting and relevant. As other online, stream-based recommender systems, they face particular challenges, including limited information on users' preferences and also rapidly fluctuating item collections. In addition, technical aspects, such as response time and scalability, must be considered. Both algorithmic and technical considerations shape working requirements for realworld recommender systems in businesses. NewsREEL represents a unique opportunity to evaluate recommendation algorithms and for students to experience realistic conditions and to enlarge their skill sets. The NewsREEL Challenge requires participants to conduct data-driven experiments in NewsREEL Replay as well as deploy their best models into NewsREEL Live's 'living lab'. This paper presents NewsREEL 2017 and also provides insights into the effectiveness of NewsREEL to support the goals of instructors teaching recommender systems to students. We discuss the experiences of NewsREEL participants as well as those of instructors teaching recommender systems to students, and in this way, we showcase NewsREEL's ability to support the education of future data scientists.