Commonplace Cultures: Mining Shared Passages in the 18th Century using Sequence Alignment and Visual Analytics
Understanding 18th Century texts using 21st Century techniques
This project is part of the JISC/NEH Digging into Data Challenge Programme 3, entitling “Commonplace Cultures: Mining Shared Passages in the 18th Century using Sequence Alignment and Visual Analytics”.
Historically, the 18th century can be seen as one of the last in a long line of commonplace cultures extending from Antiquity through the Renaissance and Early Modern periods. Here the term commonplacing denotes the thematic organization of quotations and other passages for later recall and reuse. In other words, two similar sequences in texts are potentially commonplaces. Because the measurement of similarity is typically composed of a number of metrics, and some measures are sensitive to subjective interpretation, a generic detector obtained using machine learning often has difficulties balancing the roles of different metrics according to the semantic context exhibited in a specific collection of texts.
The aim of the project was thus to devise a visual interface to enable users to construct and experiment with different detectors using primitive metrics, in a way similar to constructing an image processing pipeline.
Professor Robert Morrissey, University of Chicago
Professor Min Chen, University of Oxford
Professor Nicholas Cronk, University of Oxford
Professor Ian Foster, University of Chicago
Dr. Glenn Roe, Australian National University
Recent scholarship has demonstrated that the various rhetorical, mnemonic, and authorial practices associated with Early Modern commonplacing were highly effective strategies for dealing with the perceived “information overload” of the period, as well as for functioning successfully in polite society.
The research goal of the literature scholars in the team has been to examine this paradigm shift in 18th century culture from the perspective of commonplaces and through their textual and historical deployment over large scale text collections and across various contexts of collecting, reading, writing, classifying, and learning.
The research goal of the visualization scientists in the team has been to develop a novel visual analytics tool that can enable scholars to construct a text alignment pipeline, visualize the components and connections inside a method (i.e., a model) as well as the corresponding testing inputs and outputs.
The research in this project resulted in a software prototype, ViTA, which brings back human analytical capabilities through the use of visualization of text alignment pipelines in conjunction with testing inputs and outputs, and the use of interaction for constructing and improving such pipelines. This approach, which is referred to as model-developmental visualization, was developed in an interdisciplinary manner, and was evaluated in intensive meetings at the design stage as well as after prototyping.
The evaluation confirmed that the literature scholars can quickly accustom themselves to the pixel-based visualization. More importantly, they can use the visual interface to construct and modify text alignment pipelines. During the testing of the prototype software, the scholars in the project discovered several interesting phenomena, which stimulated new hypotheses and further research and development activities.
Open Access Software:
ViTA (Visualization for Text Alignment)
A. Abdul-Rahman, G. Roe, M. Olsen, C. Gladstone, R. Whaling, N. Cronk, R. Morrissey, and M. Chen. Constructive Visual Analytics for Text Similarity Detection, accepted by Computer Graphics Forum, 2016. DOI
G. Roe, A. Abdul-Rahman, M. Chen, C. Gladstone, R. Morrissey, and M. Olsen. Visualizing Text Alignments: Image Processing Techniques for Locating 18th-Century Commonplaces, In Digital Humanities 2015, Sydney, Australia.
- Dr. Alfie Abdul-Rahman, University of Oxford
- Dr. Mark Olsen, University of Chicago
- Clovis Gladstone, University of Chicago
- Richard Whaling, University of Chicago