# Automatic Compositor Attribution in the First Folio of Shakespeare

## TL;DR

This paper presents an unsupervised model for compositor attribution in historical printed documents, combining textual and visual features to accurately identify individual compositors, demonstrated on Shakespeare's First Folio with high agreement to expert judgments.

## Contribution

The paper introduces a novel unsupervised approach that jointly models textual and visual features for compositor attribution, improving accuracy in complex historical documents.

## Key findings

- Achieved 87% accuracy in compositor attribution on Shakespeare's First Folio.
- Model performs well even with OCR-generated text.
- Joint textual-visual modeling enhances attribution accuracy.

## Abstract

Compositor attribution, the clustering of pages in a historical printed document by the individual who set the type, is a bibliographic task that relies on analysis of orthographic variation and inspection of visual details of the printed page. In this paper, we introduce a novel unsupervised model that jointly describes the textual and visual features needed to distinguish compositors. Applied to images of Shakespeare's First Folio, our model predicts attributions that agree with the manual judgements of bibliographers with an accuracy of 87%, even on text that is the output of OCR.