Collaborative Filtering Algorithm Introduced Factor of Authority and Trust

The traditional collaborative filtering algorithm is too much emphasizing on the role of similarity of the predicted value that there have a higher Sparse Data and poor result of Recommendation. In addition to similarity, the user´s trust and authority are also an important factor that will affect the result of recommendation in the algorithm by analyzing. Proposing a new filtering method by introducing factor of authority and trust, by which the users have a more reasonable and reasonable assessment of the resources. Experiments show the effectiveness of the algorithm.