Exploratory News Recommendation

Abstract

Research on mobile news recommendation has become popular over the last few years, though the news domain is challenging and there are still few advanced commercial systems with success. This paper presents the exploratory news recommender system under development in the SmartMedia program. In exploratory news recommendation the reader can compose his own recommendation strategies on the fly and use deep semantic content analysis to extract prominent entities and navigate between relevant content at a semantic level. The readers are more likely to read a larger share of the relevant recommended articles, as there is no need to browse long tedious lists of articles or post explicit queries. The assumption is that more active and exploring readers will make implicit feedback more complete and more consistent with the readers' real interests. Tests shows a 5.14% improvement of accuracy when our collaborative filtering component is enriched with implicit feedback that combines correlations between explicit ratings with the reading times of articles viewed by readers.