Recommendation Based on Attention Degree and Entropy

With the development of the Internet, the problem of information overload becomes more and more serious. The personalized recommendation technology can establish user profiles through the user’s behavior and other information, and automatically recommend the items that best match the user’s preferences, thus effectively reducing the information overload problem. Although scholars from all over the world have proposed many solutions to the personalized news recommendation system, there are still problems such as computing redundancy, incomplete data, and the inability to make a personalized recommendation to users. Based on the problem, this paper will focus on selected IHUMCF algorithm in computing the user similarity neighbor reason is inadequate to some extent, and the attention degree impact factor is put forward, and then puts forward the L-HUMCF algorithm, and then this paper based on L-HUMCF recommended to improve, as a result, joined the user of information entropy, EL-HUMCF algorithm is proposed, and experimental verification algorithm is effective. Experimental results show that the proposed algorithm is better than other personalized recommendation algorithms.