A method for predicting citations to the scientific publications of individual researchers

Abstract

Any researcher's publications at any time can be ordered from the highest cited to the lowest cited, yielding a citation curve. We describe a novel method for predicting citation curves of researchers in the future. The method depends on treating the citation curves of researchers for various years as one single spatio-temporal function from rank and time to citations. For each researcher, we derive an estimate of this spatio-temporal function that can be used to predict the total citations of individual publications at any given rank at any time. Experiments show that this method can accurately predict entire citation curves and derived measures, such as, the total citations to all publications and the h-index of the researchers.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 15 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.