Towards a stratified learning approach to predict future citation counts

In this paper, we study the problem of predicting future citation count of a scientific article after a given time interval of its publication. To this end, we gather and conduct an exhaustive analysis on a dataset of more than 1.5 million scientific papers of computer science domain. On analysis of the dataset, we notice that the citation count of the articles over the years follows a diverse set of patterns; on closer inspection we identify six broad categories of citation patterns. This important observation motivates us to adopt stratified learning approach in the prediction task, whereby, we propose a two-stage prediction model - in the first stage, the model maps a query paper into one of the six categories, and then in the second stage a regression module is run only on the subpopulation corresponding to that category to predict the future citation count of the query paper. Experimental results show that the categorization of this huge dataset during the training phase leads to a remarkable improvement (around 50%) in comparison to the well-known baseline system.