The Paper Value Prediction Algorithm Based on the Author's Authority Value
基于作者权威值的论文价值预测算法

Citation network is a dynamic network and new papers are added to it every day. The traditional literature evaluation criteria like citations number and PageRank are unfair to the new node. How to retrieve the valuable papers of continuous concerns has become an interesting focus. To solve this problem, Hassan Sayyadi proposed the FutureRank algorithm, but it needs to calculate the PageRank value, which takes a lot of time. Accordingly, we proposed a paper value prediction algorithm without computing the PageRank value. We predict paper's rank of citations number and PageRank value in the future by writers' authority value and citer's authority value. Experimental results show that as compared with FutureRank, our algorithm not only shortens the computing time but also improves the forecast accuracy.