Evaluation of Literature Reading Value Based on User Interests Mining

A literature evaluation method based on user interest is proposed by synthesizing self-values of literature and subjective values relative to query users in this paper. Firstly, in the process of mining user interests by hierarchical clustering, vector space model is employed for expressing the literature information that reflects users download behavior and the feature space is compressed by latent semantic indexing to reduce the space dimension. Secondly, subjective value of new literature relative to researchers is quantitatively evaluated in latent semantic space. Finally, the comprehensive evaluation model of literature reading value is constructed by the transformed E-measure index based on self-value and subjective value relative to query user. Experiments show that the proposed evaluation method by fully weigh subjective and objective factors of literature is more reasonable and effective compared with the traditional evaluation methods.