Machine learning approach to predicting the acceptance of academic papers

Abstract

In this paper, machine learning approaches have been used to predict whether a scientific paper will be accepted in a top-tier AI conferences or not. This shall help authors identify the likelihood of their paper getting accepted in a top-tier AI conference. We have used the PeerRead dataset containing papers collected from major AI conferences that are publicly available. We have achieved an accuracy of 81% using Random Forest classifier. The novelty of the paper lies in accurately predicting whether a scientific paper will be accepted in the top AI conference.