摘要：Researchers have to face with huge information in their daily works. It is hard for them to screening for valuable information from huge volume of data. Reputation of literatures, publications, or scholars can help the researches to relieve their puzzle and advance their research ability. In this paper, the problem of screening is presented in a realized research platform. Reputation is modeled by synthesizing four elements: literature, author, source and reader. The perceptible interactions, such as reference, comment and P2P communication is considered to be the relationships between each pair of elements and help improve the accuracy of reputation. The reputation we build is similar to impact factor and PageRank, but it is more complex and is expected to be more robust in realistic environments, which has been proved by simulations. An iterative algorithm is introduced to evaluate reputation in a distributed mode. Simulations prove the practicality and effectiveness of the scheme we have proposed.
