"Exploratory Thematic Analysis for Historical Newspaper Archives," presented at the Digital Humanities 2014 conference in Lausanne, Switzerland. Project team: Lauren Klein, Jacob Eisenstein, and Iris Sun.

1. EXPLORATORY THEMATICANALYSIS FOR
HISTORICAL NEWSPAPER ARCHIVES
Digital Humanities 2014
Lausanne, Switzerland
9 July 2014
Jacob Eisenstein, Iris Sun, and Lauren Klein
Georgia Institute of Technology

2. Fletcher Hewes and Henry Gannett,
Statistical Atlas of the United States
(New York: Scribner’s, 1889)

3. Left: “Growth of the elements of the population: 1790 to 1890”
Right: “Church accommodations (1870)

4. “Rank of states and territories in population at each census: 1790 – 1890”

5. Newspapers in dataset
• Douglass Monthly
• Frederick Douglass Paper
• Freedom's Journal
• The Christian Recorder
• The Colored American
• The National Era
• The North Star
• The Provincial Freeman
• The Weekly Advocate
• National Anti-Slavery Standard
• The Liberator

6. T40 (“Civil Rights”): states state law constitution tho government power
united laws congress rights people con ohio tion act union question property
T55 (“Mexican-American War”): war mexico texas mexican army peace
president territory troops united government military treaty annexation
mexicans country polk taylor republic
T56 (“Native Americans”): indians indian tribes tribe chiefs frontier dian
treaties tiger hawk antelope annuity fiscal lllack hyenas tigers dians
avalanche savages
T59 (“Women’s Rights”): woman women rights husband wife sex sho
marriage property married mrs female legal sphere equality estate social
duties sexes

7. Andrew Goldstone, Model-Browser Interface

8. Objectives of EDA :
• Suggest hypotheses about the
causes of observed phenomena
• Assess assumptions on which
statistical inference will be based
• Support the selection of appropriate
tools and techniques
• Provide a basis for further data
collection through surveys or
experiments
John Tukey,
Exploratory Data Analysis
(New York: Pearson, 1977)

9. Marti Hearst et al.
WordSeer

10. Stuart Card et al., Readings in Information Visualization: Using Vision to Think (1999)

11. “A humanistic approach [to visualization]
means that the premises are rooted in the
recognition of the interpretative nature of
knowledge, that the display itself is
conceived to embody qualitative
expressions, and that the information is
understood as graphically constituted”
(129).
Johanna Drucker, Graphesis: Visual
Forms of Knowledge Production
(Cambridge: Harvard, 2014)

12. T40 (“Civil Rights”): states state law constitution tho government power
united laws congress rights people con ohio tion act union question property
T55 (“Mexican-American War”): war mexico texas mexican army peace
president territory troops united government military treaty annexation
mexicans country polk taylor republic
T56 (“Native Americans”): indians indian tribes tribe chiefs frontier dian
treaties tiger hawk antelope annuity fiscal lllack hyenas tigers dians
avalanche savages
T59 (“Women’s Rights”): woman women rights husband wife sex sho
marriage property married mrs female legal sphere equality estate social
duties sexes

14. Ji Soo Yi, Rachel Melton, John Stasko, and Julie A. Jacko
“Dust & Magnet: multivariate information visualization using a magnet metaphor”

15. TOME: Interactive TOpic Model and MEtadata Visualization, Prototype I

16. TOME: Interactive TOpic Model and MEtadata Visualization, Prototype II

17. T56 (“Native Americans”): indians indian tribes tribe chiefs frontier dian
treaties tiger hawk antelope annuity fiscal lllack hyenas tigers dians
avalanche savages

18. Multidimensional scaling
T56 (“Native Americans”):
indians indian tribes tribe chiefs
frontier dian treaties tiger hawk
antelope annuity fiscal lllack
hyenas tigers dians avalanche
savages
T55 (“Mexican-American War”):
war mexico texas mexican army
peace president territory troops
united government military treaty
annexation mexicans country polk
taylor republic

19. TOME: Interactive TOpic Model and MEtadata Visualization, Prototype II

21. Questions? Comments?
lauren.klein@lmc.gatech.edu
jacobe@gatech.edu