Predicting Citation Counts with Machine Learning: A Citation Function Approach

This paper develops a Machine Learning model to estimate the citation counts of research papers. The model uses citation functions, representing the intentions of the paper's author when making citations of previous works, to estimate the number of citations. These intentions include introducing a research topic, comparing, and criticizing previous works, etc. Three predictors have been developed based on citation functions: citing sentence, regular sentence, and reference. The prediction is seen as a regression and classification problem by pre-grouping the number of citations into high-count, medium-count, and low-count. The dataset was obtained from the International Conference on Learning Representations (ICLR) 2017–2020 containing 5,156 accepted and rejected papers. This paper uses only the accepted papers since the main task is to predict the number of citations of accepted/published papers. To obtain the number of citations one year after publication, this paper uses the API provided by Semantic Scholar. According to experiments, the best results in classification reach 98.33% accuracy, and in regression, the results reach 0.3 on both RMSE and MAE. The feature labeled ‘citing paper dominant,’ which reflects the superiority of the citing paper over the cited paper, has proven highly effective in delivering the best prediction results, even though it is sparsely represented in the dataset. In conclusion, citation function-based predictors are effective in estimating the future impact of a paper.