A News Recommendation Algorithm Based on Deep Learning

It has become a trend to obtain news information through network media, but everyone has different tendencies. People are more willing to browse the news they are interested in, so news recommendation becomes very important. The recommendation algorithm can screen out the news that the user is interested in from the massive information, so as to alleviate the problem of information overload in the era of big data. Deep learning model, this paper used to mining the characteristics of the users and news, to learn and build the model, the traditional recommendation algorithm of sparse matrix and the disadvantage of cold start, the experimental results show that this model adopted by the run on Adressa 1G data set is good, at the same time, accuracy and recall rate compared with the traditional collaborative filtering algorithm is improved, so this recommendation works well.