Abstract
News recommendations play an important role in daily life, but there is a problem of privacy leakage. To address this problem, a news recommendation method for user privacy protection is proposed. It combines news recommendation with a federated learning framework to ensure accurate recommendations while protecting user privacy. To be specific, the method contains three key components: 1) It combines federated learning to ensure that user data is processed locally and not leaked to third parties, thus achieving privacy protection. 2) It fully considers the long-term and short-term interests of users and learns their short-term interests using the GRU model based on the item features of interaction, which provides a more comprehensive perspective on user modelling. 3) We design a score prediction method that fuses linear and nonlinear features to better capture the interaction between users and news and improve the accuracy of recommendation. The experimental validation on two public news datasets, Adressa and MIND, demonstrates that the method can still achieve efficient news recommendation without compromising user privacy.