The quantity of information available to scholars has increased to the point that many choose to specialize, and thereby reduce the quantity of relevant information down to a level that is manageable. However, even interpretations in narrowly defined domains are influenced by their context. This dissertation focuses on methodologies that can lead to greater intelligence of the data. It discusses the applicability of model-making to questions in history, and proposes a method to take into account a large amount of text information in the development of historical interpretations. The method applies recent advances in Large Language Models (LLMs) and graph representation of information to produce a variety of visualizations and statistical measures which aid the scholar in producing a more complete interpretation of a given topic by mapping its context over hundreds or thousands of scholarly works. Throughout the thesis examples are given of interpretive questions in Mesopotamian history, especially in the interpretation of Mesopotamian religion. All programs developed in the dissertation were written by the author.
The quantity of information available to scholars has increased to the point that many choose to specialize, and thereby reduce the quantity of relevant information down to a level that is manageable. However, even interpretations in narrowly defined domains are influenced by their context. This dissertation focuses on methodologies that can lead to greater intelligence of the data. It discusses the applicability of model-making to questions in history, and proposes a method to take into account a large amount of text information in the development of historical interpretations. The method applies recent advances in Large Language Models (LLMs) and graph representation of information to produce a variety of visualizations and statistical measures which aid the scholar in producing a more complete interpretation of a given topic by mapping its context over hundreds or thousands of scholarly works. Throughout the thesis examples are given of interpretive questions in Mesopotamian history, especially in the interpretation of Mesopotamian religion. The programs developed in the dissertation were written by the author.
Method and Intelligence. Digital Approaches to Memory and Communication in Historiography
LYNCH, JONAH HEER
2024
Abstract
The quantity of information available to scholars has increased to the point that many choose to specialize, and thereby reduce the quantity of relevant information down to a level that is manageable. However, even interpretations in narrowly defined domains are influenced by their context. This dissertation focuses on methodologies that can lead to greater intelligence of the data. It discusses the applicability of model-making to questions in history, and proposes a method to take into account a large amount of text information in the development of historical interpretations. The method applies recent advances in Large Language Models (LLMs) and graph representation of information to produce a variety of visualizations and statistical measures which aid the scholar in producing a more complete interpretation of a given topic by mapping its context over hundreds or thousands of scholarly works. Throughout the thesis examples are given of interpretive questions in Mesopotamian history, especially in the interpretation of Mesopotamian religion. All programs developed in the dissertation were written by the author.File | Dimensione | Formato | |
---|---|---|---|
method and intelligence FINAL VERSION.pdf
accesso aperto
Dimensione
5.26 MB
Formato
Adobe PDF
|
5.26 MB | Adobe PDF | Visualizza/Apri |
I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/20.500.14242/158386
URN:NBN:IT:UNIPV-158386