Predicting New Concept-Object Associations in Astronomy by Mining the Literature

2026-02-15

AI Summary

This work proposes a novel method for predicting yet-unpublished concept–celestial object associations from astronomical literature to inform the prioritization of telescope observation targets. By constructing a knowledge graph driven by astro-ph publications—integrating OCR-based text processing, SIMBAD entity alignment, and scientific concept clustering—the approach uniquely combines implicit-feedback matrix factorization (via Alternating Least Squares) with a KNN-based text embedding strategy that smooths concept semantic similarity. Experimental results demonstrate that the method outperforms the strongest baseline by 16.8% in NDCG@100 and 19.8% in Recall@100, significantly surpassing existing heuristic and neighborhood-based approaches. These findings substantiate that the structure of scientific discovery embedded within the literature is inherently predictable.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Learning Preferences or Rankings
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Web Mining and Content Analysis: Interdisciplinary science discovery with web data mining

Abstract

We construct a concept-object knowledge graph from the full astro-ph corpus through July 2025. Using an automated pipeline, we extract named astrophysical objects from OCR-processed papers, resolve them to SIMBAD identifiers, and link them to scientific concepts annotated in the source corpus. We then test whether historical graph structure can forecast new concept-object associations before they appear in print. Because the concepts are derived from clustering and therefore overlap semantically, we apply an inference-time concept-similarity smoothing step uniformly to all methods. Across four temporal cutoffs on a physically meaningful subset of concepts, an implicit-feedback matrix factorization model (alternating least squares, ALS) with smoothing outperforms the strongest neighborhood baseline (KNN using text-embedding concept similarity) by 16.8% on NDCG@100 (0.144 vs 0.123) and 19.8% on Recall@100 (0.175 vs 0.146), and exceeds the best recency heuristic by 96% and 88%, respectively. These results indicate that historical literature encodes predictive structure not captured by global heuristics or local neighborhood voting, suggesting a path toward tools that could help triage follow-up targets for scarce telescope time.

Problem

• concept-object association
• astronomy
• literature mining
• knowledge graph
• prediction

Innovation

• knowledge graph
• matrix factorization
• concept-object association
• literature mining
• astronomical discovery