Metadata in the Margins
1
Reshaping Archives as Data through Early Modern Marginalia
1.1
Abstract
1.2
Acknowledgements
2
Introduction
3
Marginalia in the Archive
3.1
The Historiography of Marginalia
3.2
Presence in Physical and Digital Archives
3.2.1
How is Marginalia defined?
3.2.2
Physical and Digital Presence
3.3
On Object Marks and Machines
4
Creation of an Application to Capture the Metadata of Big Data
4.1
Technical Overview
4.2
Process
4.2.1
Interface and Tooling
4.2.2
Annotation and Metadata
5
Case Study: Finding Early Modern Marginalia
5.1
Understanding Big Data
5.2
The Cultural Heritage Collection as Data
5.2.1
NLS Chapbooks in the Data Foundry
5.2.2
The Archaeology of Reading
5.2.3
Early Modern Annotated Books
5.2.4
Dataset Provenance
5.3
Annotation Process and Dataset Formation
5.4
The Machine Learning Model
5.5
Results
5.5.1
False Positives
5.5.2
Man vs Machine
5.6
Discussion
6
Conclusions
6.1
Future Directions
6.2
Closing Thoughts
References
7
Appendix A: The Full “Collections as ML Data” Checklist
Published with bookdown
Metadata in the Margins
References