Predicting the Citations of Scholarly Paper

TL;DR

This paper introduces two models for predicting scholarly paper citations, leveraging inherent properties and multiple features, with the PPI model offering superior interpretability and the multi-feature model providing better accuracy under certain metrics.

Contribution

The paper proposes the PPI model based on four factors and a multi-feature model for citation impact prediction, advancing understanding of citation dynamics and improving prediction accuracy.

Findings

PPI model outperforms in range-normalized RMSE.

Multi-feature model achieves better MAPE and accuracy.

Both models enhance citation prediction accuracy.

Abstract

Citation prediction of scholarly papers is of great significance in guiding funding allocations, recruitment decisions, and rewards. However, little is known about how citation patterns evolve over time. By exploring the inherent involution property in scholarly paper citation, we introduce the Paper Potential Index (PPI) model based on four factors: inherent quality of scholarly paper, scholarly paper impact decaying over time, early citations, and early citers' impact. In addition, by analyzing factors that drive citation growth, we propose a multi-feature model for impact prediction. Experimental results demonstrate that the two models improve the accuracy in predicting scholarly paper citations. Compared to the multi-feature model, the PPI model yields superior predictive performance in terms of range-normalized RMSE. The PPI model better interprets the changes in citation, without the need to adjust parameters. Compared to the PPI model, the multi-feature model performs better prediction in terms of Mean Absolute Percentage Error and Accuracy; however, their predictive performance is more dependent on the parameter adjustment.