Predicting Citation Counts with a Neural Network

TL;DR

This paper introduces a neural network model that predicts future citation counts of researchers using their past publication data, showing improved predictability for arXiv.org publications compared to previous methods.

Contribution

It presents a simple neural network approach that enhances citation count prediction accuracy, especially for open access publications.

Findings

Higher predictability for arXiv.org publications

Neural network outperforms previous models

Effective use of past researcher data

Abstract

We here describe and present results of a simple neural network that predicts individual researchers' future citation counts based on a variety of data from the researchers' past. For publications available on the open access-server arXiv.org we find a higher predictability than previous studies.