Predicting promising academic papers is useful for a variety of parties, including researchers, universities, scientific councils, and policymakers. Researchers may benefit from such data to narrow down their reading list and focus on what will be important, and policymakers may use predictions to infer rising fields for a more strategic distribution of resources.This research focuses on developing novel techniques to predict a paper’s future impact (e.g., number of citations). We employ temporaland topological features derived from citation networks. In addition, we use a behavioral modeling approach to identify different families of papers in terms of their expected impact. We also adapt information diffusion paradigm into the citation networks to track the follow of ideas proposed by different papers.



  • Feruz Davletov, Ali Selman Aydin, Ali Cakmak. "High Impact Academic Paper Prediction Using Temporal and Topological Features". ACM International Conference on Information and Knowledge Management ACM CIKM 2014, November 3-7, Shanghai, China.