Knowledge Graph in Astronomical Research with Large Language Models: Quantifying Driving Forces in Interdisciplinary Scientific Discovery
Keywords: Large language model, Knowledge Graph, Interdisciplinary Research, Citation-Reference Relation, Driving Force for Scientific Discovery
TL;DR: Using large language models, this study analyzes 297,807 astronomy articles to quantify the impact of interdisciplinary research through a knowledge graph.
Abstract: Identifying and predicting the factors that contribute to the success of interdisciplinary research is crucial for advancing scientific discovery. However, there is a significant lack of methods to quantify the integration of new ideas and technological advancements within a field and how they trigger further scientific breakthroughs. Large language models, with their prowess in extracting key concepts from vast literature beyond keyword searches, provide a new tool to quantify such processes. In this study, we use astronomy as a case study to quantify this process. We extract concepts in astronomical research from 297,807 publications between 1993 and 2024 using large language models, resulting in a refined set of 24,939 concepts. These concepts are then adopted to form a knowledge graph, where the link strength between any two concepts is determined by their relevance based on the citation-reference relationships. By calculating this relevance across different time periods, we quantify the impact of numerical simulations and artificial intelligence on astronomical research, demonstrating the possibility of quantifying the gradual integration of interdisciplinary research and its further branching that leads to the flourishing of scientific domains.
Submission Number: 8
Loading