A Personalized News Recommendation Algorithm Integrating User Comments

Abstract

With the explosive growth of the number of news, how to help users efficiently and accurately find the news they are interested in from the mass of news has become more and more important. The traditional collaborative filtering news recommendation algorithm is based on user browsing records. However, the user's browsing history cannot directly indicate the user's preference for news. Meanwhile, the degree of correlation between user comments and news can intuitively reflect the degree of interest of users in news. Thus, a personalized news recommendation algorithm incorporating user comments is proposed. Firstly, the algorithm proposes a calculation method of user similarity, which integrates the influence of news popularity and the text characteristics of user comments. Secondly, we integrate the correlation between comments and news into the calculation of user's news preference, and measures the confidence of user's news browsing records according to the correlation level. Finally, we evaluate our approach with a large number of experiments. The experimental results show that the personalized news recommendation algorithm combined with user comments has significantly improved the recommendation effect compared with other algorithms.