Historical insights at scale: A corpus-wide machine learning analysis of early modern astronomic tables

Oliver Eberle ^{1, 2}

Jochen Büttner ^{2, 3}

Hassan El Hajj ^{2, 4}

Grégoire Montavon ^{1, 2, 5}

Klause Muller ^{1, 2, 6, 7}

Matteo Valleriani ^{2, 4, 8, 9}

Hide authors affiliations

Machine Learning Group, Technische Universität Berlin, Marchstr. 23, 10587 Berlin, Germany. |

BIFOLD–Berlin Institute for the Foundations of Learning and Data, 10587 Berlin, Germany. |

Max Planck Institute of Geoanthropology, Kahlaische Str. 10, 07745 Jena, Germany. |

⁴

Max Planck Institute for the History of Science,Boltzmannstr. 22, 14195 Berlin, Germany. |

⁵

Department of Mathematics and Computer Science, Freie Universität Berlin, Arnimallee 14, 14195 Berlin, Germany. |

⁶

Department of Artificial Intelligence, Korea University, Seoul 136-713, South Korea. |

⁷

Max Planck Institute for Informatics, Stuhlsatzenhausweg 4, 66123 Saarbrücken, Germany. |

⁸

Institute of History and Philosophy of Science, Technology, and Literature, Faculty I–Humanities and Educational Sciences, Technische Universität Berlin, Straße des 17. Juni 135, 10623 Berlin, Germany. |

⁹

The Cohn Institute for the History and Philosophy of Science and Ideas, Faculty of Humanities, Tel Aviv University, P.O. Box 39040, Ramat Aviv, Tel Aviv 6139001, Israel. |

Publication type: Journal Article

Publication date: 2024-10-25

American Association for the Advancement of Science (AAAS)

Journal: Science advances

scimago Q1

SJR: 4.483

CiteScore: 21.4

Impact factor: 11.7

ISSN: 23752548

DOI: 10.1126/sciadv.adj1719

Copy DOI

Abstract

Understanding the evolution and dissemination of human knowledge over time faces challenges due to the abundance of historical materials and limited specialist resources. However, the digitization of historical archives presents an opportunity for AI-supported analysis. This study advances historical analysis by using an atomization-recomposition method that relies on unsupervised machine learning and explainable AI techniques. Focusing on the “Sacrobosco Collection,” consisting of 359 early modern printed editions of astronomy textbooks from European universities (1472–1650), totaling 76,000 pages, our analysis uncovers temporal and geographic patterns in knowledge transformation. We highlight the relevant role of astronomy textbooks in shaping a unified mathematical culture, driven by competition among educational institutions and market dynamics. This approach deepens our understanding by grounding insights in historical context, integrating with traditional methodologies. Case studies illustrate how communities embraced scientific advancements, reshaping astronomic and geographical views and exploring scientific roots amidst a changing world.

Found

	1
Information Fusion	Information Fusion, 1, 50% Information Fusion 1 publication, 50%
Nature Machine Intelligence	Nature Machine Intelligence, 1, 50% Nature Machine Intelligence 1 publication, 50%
	1