Replicating a Citation Context Analysis using Natural Language Processing Methods

Ye, Zhiheng

Permalink

https://hdl.handle.net/2142/123191 Copy

Description

Title

Replicating a Citation Context Analysis using Natural Language Processing Methods

Author(s)

Ye, Zhiheng

Contributor(s)

• Sarol, Janina
• Schneider, Jodi

Issue Date

2024-04-25

Keyword(s)

Citation Context Analysis, NLP

Abstract

Citations allow publication authors to acknowledge original contributions and provide evidence for claims, facilitating further exploration, ensuring transparency and integrity, and paving the way to trace the evolution of scientific thought. By closely examining the textual content of citations (citation context analysis), we can assess how publications and authors are utilized, tested, and critiqued in subsequent literature [1]. Citation context analysis offers a systematic way to assess the impact of theories and improve citation practices across science. Earlier studies often used manual methods for compiling and analyzing citation contexts. However, manual collection and analysis cannot be used to find generalizable discoveries reliably [2]. The sheer volume of scientific literature to be analyzed, the nuanced interpretations required to understand the context and intent of citations, and the fact that conducting these studies is time-consuming make it infeasible to manually conduct large-scale citation context studies. This project explores the feasibility of using natural language processing to conduct citation context analysis studies automatically. In particular, we apply named entity recognition and relation extraction methods to automatically replicate a previous study that examined how a paper about the association between diet and coronary heart disease was cited. [1] Anderson, M. H., & Lemken, R. K. (2023). Citation Context Analysis as a Method for Conducting Rigorous and Impactful Literature Reviews. Organizational Research Methods, 26(1), 77–106. https://doi.org/10.1177/1094428120969905 [2] Bornmann, L., Wray, K. B., & Haunschild, R. (2020). Citation concept analysis (CCA): A new form of citation analysis revealing the usefulness of concepts for other researchers illustrated by exemplary case studies including classic books by Thomas S. Kuhn and Karl R. Popper. Scientometrics, 122(2), 1051–1074. https://doi.org/10.1007/s11192-019-03326-2

Type of Resource

• text
• still image

Language

eng

Sponsor(s)/Grant Number(s)

Alfred P. Sloan Foundation G-2022-19409

Owning Collections