Abstract-Because of the abundance of news on the web, news recommendation is an important problem. We compare three approaches for personalized news recommendation: collaborative filtering at the level of news items, content-based system recommending items with similar topics, and a hybrid technique.We observe that recommending items according to the topic profile of the current browsing session seems to give poor results. Although news articles change frequently and thus data about their popularity is sparse, collaborative filtering applied to individual articles provides the best results.

Abstract.Exploratory search over a collection often requires users to iteratively apply a variety of strategies, such as searching for more general or more specific concepts in reaction to the information they encounter. Rich semantic models, such as WordNet, are potentially valuable aids for making sense of this information. However, these large complex models often contain specialized vocabularies and a detailed level of granularity that makes them difficult to use for opportunistic search. In this paper, we describe how Semantic Fisheye Views (SFEV) can be designed to transparently integrate rich semantic models into the search process, allowing users to effectively explore a diverse range of related concepts without explicitly navigating over the underlying model. The SFEV combines semantic guided search with interactive visualization techniques, creating a search tool that we have found to be significantly more effective for exploratory tasks than those based on keyword-similarity alone.

We describe the selection, implementation and online evaluation of two e-commerce recommender systems developed with our partner company, Prediggo. The first one is based on the novel method of Bayesian Variable-order Markov Modeling (BVMM). The second, SSAGD, is a novel variant of the Matrix-Factorization technique (MF), which is considered state-of-the-art in the recommender literature.We discuss the offline tests we carried out to select the best MF variant, and present the results of two A/B tests performed on live ecommerce websites after the deployment of the new algorithms. Comparing the new recommenders and Prediggo’s proprietary algorithm of Ontology Filtering, we show that the BVMM significantly outperforms the two others in terms of CTR and prediction speed, and leads to a strong increase in recommendation-mediated sales. Although MF exhibits reasonably good accuracy, the BVMM is still significantly more accurate and avoids the high memory requirements of MF. This scalability is essential for its application in online businesses.