Detecting text level intellectual influence with knowledge graph embeddings
This provides a computational tool for researchers in fields like intellectual history and science of science to trace idea spread, though it appears incremental as it builds on existing knowledge graph methods.
The paper tackled the problem of detecting intellectual influence between academic articles by predicting citation relationships using knowledge graph embeddings, and demonstrated that their novel Graph Neural Network-based embedding method was superior at distinguishing cited vs. non-cited article pairs.
Introduction: Tracing the spread of ideas and the presence of influence is a question of special importance across a wide range of disciplines, ranging from intellectual history to cultural analytics, computational social science, and the science of science. Method: We collect a corpus of open source journal articles, generate Knowledge Graph representations using the Gemini LLM, and attempt to predict the existence of citations between sampled pairs of articles using previously published methods and a novel Graph Neural Network based embedding model. Results: We demonstrate that our knowledge graph embedding method is superior at distinguishing pairs of articles with and without citation. Once trained, it runs efficiently and can be fine-tuned on specific corpora to suit individual researcher needs. Conclusion(s): This experiment demonstrates that the relationships encoded in a knowledge graph, especially the types of concepts brought together by specific relations can encode information capable of revealing intellectual influence. This suggests that further work in analyzing document level knowledge graphs to understand latent structures could provide valuable insights.