Reading Chicago Reading: Modeling Texts and Readers in a Public Library System

FAIN: HD-248600-16

DePaul University (Chicago, IL 60604-2201)
John Shanahan (Project Director: September 2015 to April 2022)
Robin Burke (Co Project Director: March 2016 to April 2022)
Antonio Ceraso (Co Project Director: March 2016 to October 2016)
Megan Bernal (Co Project Director: March 2016 to May 2018)
Ana Lucic (Co Project Director: October 2016 to April 2022)

A pilot study on how analyzing patron responses to a citywide reading program can help scholars and librarians better understand which book genres and styles prove most meaningful to the community.

“Reading Chicago Reading” aims to put new data-intensive predictive tools in the hands of public librarians and digital humanities scholars in order to enhance their ability to serve public needs and interests. We take as our starting point the Chicago Public Library’s popular and muchimitated “One Book One Chicago” program, in which books are annually selected for city-wide promotion. Our project combines circulation data, social media postings, text analysis, branch-bybranch demographics, and history of the events of themselves to recover quantitative, predictive factors that link texts to reader response. The multi-disciplinary project brings together expertise in library science, text mining, predictive modeling and machine learning, literature, and urban sociology, and builds on existing collaborations with the Chicago Public Library.

Associated Products

Reading Chicago Reading Wins Start-Up Grant (Blog Post)
Title: Reading Chicago Reading Wins Start-Up Grant
Author: Lisa Peet
Abstract: Coverage about the project in _Library Journal_.
Date: 05/18/2016
Primary URL: http://lj.libraryjournal.com/2016/05/books-media/reading-chicago-reading-wins-start-up-grant/#_
Primary URL Description: Page for the article about our "Reading Chicago Reading" project
Secondary URL: http://dh.depaul.press/reading-chicago/
Secondary URL Description: Our project's blog.
Blog Title: Reading Chicago Reading

DAta Sources for Modeling Library Texts and Readership (Conference Paper/Presentation)
Title: DAta Sources for Modeling Library Texts and Readership
Author: Robin Burke, John Shanahan
Abstract: Presentation of funded project's findings at the Second Annual International Conference on Quantitative Social Science, at Northwestern University
Date: 06/25/2016
Conference Name: Second Annual International Conference on Quantitative Social Science

Reading Chicago Reading (Web Resource)
Title: Reading Chicago Reading
Author: John Shanahan
Author: Robin Burke
Author: Ana Lucic
Abstract: “Reading Chicago Reading” is a digital humanities project that takes as its starting point the popular and much-imitated “One Book, One Chicago” (OBOC) program operated by the Chicago Public Library (CPL) since 2001. Each year (originally every six months), the library chooses one book around which to organize city-wide events, discussions, and other programming. For our purposes, the OBOC program acts as a natural experiment. The 25 different books that have been chosen since the program’s inception can be thought of as probes into the reading behavior of the city. The dependent variables of interest are, of course, the patterns of reading behavior that these probes elicit. We make use of scholarship in the history and sociology of reading as an interpretive baseline representing the standard approach. But our study, by bringing together Computer Science and Humanities research methods, promises new kinds of insight and new forms of quantifiable data.
Year: 2016
Primary URL: https://dh.depaul.press/reading-chicago/

Circulation Modeling of Library Book Promotions (Conference Paper/Presentation)
Title: Circulation Modeling of Library Book Promotions
Author: Robin Burke
Author: Ana Lucic
Author: John Shanahan
Abstract: Community reading initiatives, in which a book is selected for system-wide reading and discussion, have become common in many library systems. This paper describes the initial findings in a demographic study of the "One Book, One Chicago" initiative by the Chicago Public Library. Using a multilevel linear model, we show that, over six recent offerings of the "One Book" program, the books vary widely in their uptake by library patrons at different branches, and these differences cannot be entirely explained by demographics or the library's promotional strategies. We thus motivate the next stage of our project, which is to incorporate representations of book content and reader response into the model.
Date: 6/19/2017
Primary URL: https://dl.acm.org/citation.cfm?id=3200378
Primary URL Description: Published in JCDL '17 Proceedings of the 17th ACM/IEEE Joint Conference on Digital Libraries (Pages 291-292)
Conference Name: Joint Conference on Digital Libraries 2017

Reading Chicago Reading: Quantitative Analysis of a Repeating Literary Program (Article)
Title: Reading Chicago Reading: Quantitative Analysis of a Repeating Literary Program
Author: Robin Burke
Author: John Shanahan
Author: Ana Lucic
Abstract: This essay presents quantitative capture and predictive modeling for one of the largest and longest running mass reading programs of the past two decades: “One Book One Chicago” (OBOC) sponsored by the Chicago Public Library (CPL). The Reading Chicago Reading project uses data associated with OBOC as a probe into city-scale library usage and, by extension, as a window onto contemporary reading behavior. The first half of the essay explains why CPL’s OBOC program is conducive for modeling purposes, and the second half documents the creation of our models, their underlying data, and the results.
Year: 2020
Primary URL: http://www.digitalhumanities.org/dhq/vol/14/2/000461/000461.html
Primary URL Description: Article page: http://www.digitalhumanities.org/dhq/vol/14/2/000461/000461.html
Access Model: Open Access Peer-Reviewed
Format: Journal
Periodical Title: Digital Humanities Quarterly
Publisher: Digital Humanities Quarterly

Toward a Chicago Place Name Dataset: From Back-of-the-Book Index to a Labeled Dataset (Article)
Title: Toward a Chicago Place Name Dataset: From Back-of-the-Book Index to a Labeled Dataset
Author: John Shanahan
Author: Ana Lucic
Abstract: Description of project work using machine learning tools to convert a book index to a dataset for Chicago placenames. The work arose from Reading Chicago Reading mapping tasks. It documents some ways librarians and literary and digital humanities scholars can collaborate.
Year: 2021
Access Model: Open Access
Format: Other
Periodical Title: Machine Learning, Libraries, and Cross-Disciplinary Research: Possibilities and Provocations
Publisher: University of Notre Dame Press

Unsupervised Clustering with Smoothing for Detecting Paratext Boundaries in Scanned Documents (Article)
Title: Unsupervised Clustering with Smoothing for Detecting Paratext Boundaries in Scanned Documents
Author: John Shanahan
Author: Ana Lucic
Author: Robin Burke
Abstract: Digital humanities scholars are developing new techniques of literary study using non-consumptive processing of large collections of scanned text. A crucial step in working with such collections is to separate the main text of a work from the surrounding paratext, the content of which may distort word counts, location references, sentiment scores, and other important outputs. Simple heuristic methods have been devised, but are not accurate for some texts and some methodological needs. This study describes a method for paratext detection based on smoothed unsupervised clustering. We show that this method is more accurate than simple heuristics, especially for non-fiction works, and edited works with larger amounts of paratext. We also show that a more accurate detection of paratext boundaries improves the accuracy of subsequent text processing, as exemplified by a readability metric.
Year: 2019
Primary URL: https://ieeexplore.ieee.org/abstract/document/8791148
Format: Journal
Periodical Title: IEEE/ACM Joint Conference on Digital Libraries (JCDL)
Publisher: IEEE Explore

Circulation Modeling of Library Book Promotions (Article)
Title: Circulation Modeling of Library Book Promotions
Author: John Shanahan
Author: Robin Burke
Author: Ana Lucic
Abstract: Community reading initiatives, in which a book is selected for system-wide reading and discussion, have become common in many library systems. This paper describes the initial findings in a demographic study of the ``One Book, One Chicago'' initiative by the Chicago Public Library. Using a multilevel linear model, we show that, over six recent offerings of the ``One Book'' program, the books vary widely in their uptake by library patrons at different branches, and these differences cannot be entirely explained by demographics or the library's promotional strategies. We thus motivate the next stage of our project, which is to incorporate representations of book content and reader response into the model.
Year: 2017
Primary URL: https://ieeexplore.ieee.org/document/7991595
Format: Journal
Periodical Title: IEEE/ACM Joint Conference on Digital Libraries (JCDL)
Publisher: IEEE Explore

---