A Personalized Recommendation Algorithm Based on Time Factor and Reading Factor

With the rapid development of the Internet, the data in news, information, education and other application platforms are exploding, which has brought serious information overloading problems to Internet users. The recommendation algorithm is an effective solution to help Internet users select the valuable information from high volume data. Traditional recommendation algorithms ignore the change of users' interest over time and cannot provide users with effective and reasonable recommendation lists. To solve the above problems, this paper proposes a personalized recommendation method that time factor and reading factor into consideration. This method retrieves and compute time factor and reading factor in the process of user tag selection and then produce customized information recommendation list tailored for users. The experiment shows that the accuracy of our algorithm is higher than the traditional recommendation algorithm by considering time factor and reading factor.