Data Sets and News Recommendation.
Özlem Özgöbek, Nafiseh Shabib, Jon Atle Gulla · International Conference on User Modeling, Adaptation, and Personalization · 2014
Datasets are important for training and testing many information processing applications. In the field of news recommendation, there are still few available datasets, and many feel obliged to use nonnews datasets to test their algorithms for news recommendation. This paper presents some of the most common datasets for recommender systems in general, and explains why these datasets do not fully satisfy the needs in news recommendation. We then discuss the ongoing process of building up an entirely new dataset for Norwegian news in the SmartMedia project. In particular, we go through some of the features of news datasets that separate them from many other datasets and are crucial for their use in news recommendation.