Author : Miss.Kshitija G. Deshmukh and Prof.Dr.(Mrs) S. A. Itkar

Various research papers are published online and offline, and as new research fields have been continuously created, users have tons of trouble in finding and categorizing their attention-grabbing research papers. The proposed system extract the abstracts of each paper then, it removes the stop word by preprocessing method and it also removes the suffix of word by using stemming technique. The stemming technique is used to reduce the high dimensionality of the feature space. Then, the Recurrent Neural Network (RNN) algorithm is applied to classify the research papers with similar subjects, based on the Term frequency-inverse document frequency (TF-IDF) values of each paper.

Keywords: Research Paper Classification, Recurrent Neural Network, Categorization, Stemming Technique.