Originality in scientific titles and abstracts can predict citation count

TL;DR

This study introduces a computational measure called Divergent Semantic Integration (DSI) to quantify originality in scientific titles and abstracts, demonstrating its correlation with citation counts across various research fields.

Contribution

The paper applies DSI to a large dataset of scientific abstracts and titles, revealing its potential to predict citation impact and its variation across disciplines and over time.

Findings

DSI varies significantly between research fields.

A positive correlation exists between DSI and 5-year citation counts.

DSI shows a slight increase over time.

Abstract

In this research-in-progress paper, we apply a computational measure correlating with originality from creativity science: Divergent Semantic Integration (DSI), to a selection of 99,557 scientific abstracts and titles selected from the Web of Science. We observe statistically significant differences in DSI between subject and field of research, and a slight rise in DSI over time. We model the base 10 logarithm of the citation count after 5 years with DSI and find a statistically significant positive correlation in all fields of research with an adjusted $R^2$ of 0.13.