Program

Digital Humanities: Digital Humanities Advancement Grants

Period of Performance

9/1/2019 - 12/31/2020

Funding Totals

$99,497.00 (approved)
$99,497.00 (awarded)


Intertextual Bridges: Search and Navigation across Heterogeneous Collections

FAIN: HAA-266518-19

University of Chicago (Chicago, IL 60637-5418)
Robert Morrissey (Project Director: January 2019 to present)

The development of a prototype platform that will allow scholars to combine distant and close reading methods to discover relationships between texts and identify texts in collections for further study.

We seek Level II funding for a pilot project to develop a model that will allow scholars to bridge the gap between distant and close reading when conducting research on large, heterogeneous digital text collections. We propose to create a language agnostic environment—called the Intertextual Hub—in which the conceptual relationships among texts discovered by text-mining algorithms can fruitfully guide close reading in dialectical interaction with distant reading. Fundamentally, we are contending that the core of scholarly reading in the digital age should be the discovery and navigation of intertextual relationships. The Intertextual Hub will be a powerful hermeneutical device allowing users to navigate between individual texts and larger corpora that are related through shared themes, ideas, and passages. Focusing on the French Revolutionary period, we will test this model by applying it to the extensive and diverse 18th-century French collections of UChicago’s ARTFL Project.





Associated Products

TopoLogic (Computer Program)
Title: TopoLogic
Author: Clovis Gladstone
Abstract: TopoLogic, a Topic Model generator and navigation system which is also available on GitHub: https://github.com/ARTFL-Project/TopoLogic TopoLogic builds value-added services on top of the standard PhiloLogic index, leveraging topic-modeling techniques to offer an alternate way of exploring text collections. Topic-modeling, the algorithmic technique which we use for this new navigational tool, is an unsupervised machine learning approach designed to facilitate the exploration of large collections of texts where no topical information is provided. As such, this computational method can be a truly useful way of gaining a sense of the topical structure of a corpus -- i.e. to find out what's in there -- and how words are clustered together to form meaningful discourses. TopoLogic builds upon the topics and semantic fields generated by the algorithm to provide a web-based navigation system which lets users explore topics and discourses across time, as well as word usage within different contexts. The interaction of the three different schemes allows the user to navigate between alternative ways of considering topics across the collection.
Year: 2020
Primary URL: https://github.com/ARTFL-Project/TopoLogic
Primary URL Description: Source Code
Secondary URL: https://artflsrv03.uchicago.edu/topic-modeling-browser/frc1787_99/
Secondary URL Description: Full Function Example
Access Model: Open Access
Programming Language/Platform: Python/Javascript
Source Available?: Yes

The Intertextual Hub: Search and Navigation across Digital Collections (Web Resource)
Title: The Intertextual Hub: Search and Navigation across Digital Collections
Author: Robert Morrissey
Abstract: The Intertextual Hub is an experimental digital humanities reading environment that aims to situate specific documents in their broader context of intertextual relations, whether in the form of direct or indirect borrowings, shared topics with other texts or parts of texts, or other kinds of lexical similarity. Intuitively, we believe that he conceptual relationships discovered by text mining algorithms among texts in large, heterogeneous collections can fruitfully inform and guide traditional close-reading approaches. More fundamentally, our contention is that scholarly reading in the digital age—and the true usefulness of computational analysis of texts—should be foregrounded on the discovery and navigation of intertextual relationships. The model we have developed here allows users to navigate between individual and larger groups of texts that are related through shared themes, ideas, and passages. What the Intertextual Hub offers, then, along with the scalable reading tools, is an approach to federating collections that can bypass the various competing problems of quality (OCR vs. curated) and access (pay vs. public) inherent in digital collections today, and still yield meaningful results.
Year: 2021
Primary URL: https://intertextual-hub.org/

ARTFL Text Preprocessing Library (Computer Program)
Title: ARTFL Text Preprocessing Library
Author: Clovis Gladstone
Abstract: This code extracts consistent, structured data from PhiloLogic4 database instances that is required for cross-collection processing, search, and navigation. We use this extracted data for global search and retrieval, generating topic models on individual collections, performing sequence alignment across collections, and generating topic based text segments. The library allows us to leverage PhiloLogic4 services to enhance search, reporting, and navigation.
Year: 2019
Primary URL: https://github.com/ARTFL-Project/text-preprocessing
Access Model: Open Access
Source Available?: Yes