Date post: | 15-Apr-2017 |
Category: |
Education |
Upload: | keystone-dh-2016 |
View: | 53 times |
Download: | 0 times |
What Made the Front Page in the 19th Century?
Computationally Classifying Genre in “Viral Texts”
Jonathan D. Fitzgerald Northeastern University
@jon_fitzgerald
Ryan Cordell, “Reprinting, Circulation, and the Network Author in Antebellum Newspapers”
“When every nineteenth-century newspaper brims with original and reprinted content of all kinds, it is difficult to know where to even begin studying that content.”
@jon_fitzgerald
@jon_fitzgerald
Christof Schöch, “Topic Modeling Genre: An Exploration of French Classical and Enlightenment Drama”
“The concept of literary genre is a highly complex one: not only are different genres frequently defined on several, but not necessarily the same levels of description, but consideration of genres as cognitive, social, or scholarly constructs with a rich history further complicate the matter.”
@jon_fitzgerald
Ted Underwood, “Understanding Genre in a Collection of a Million Volumes"
“Centuries of literary scholarship have failed to produce human consensus about genre.”
@jon_fitzgerald
Ted Underwood, “Distant reading and the blurry edges of genre”
“The model was trained, after all, on examples tagged by human beings; the whole point of doing that was to reproduce as much as possible the contours of the boundary that separates genres for us.”
@jon_fitzgerald
Benjamin Schmidt, “Genre Classification from Topic models”
“To reduce dimensionality into the model, we have been thinking of using a topic model as the classifiers instead of the tokens. The idea is that classifiers with more than several dozen variables tend to get finicky and hard to interpret, and with more than a few hundred become completely unmanageable.”
@jon_fitzgerald
Topic Model of 4,000 Clusters
god life world heart love man time good men make
court sir called judge de states government united congress made
tbe jones _ trumble noble 000 10 cent year 30
tile thle tie tihe thie water feet cold hot put
years hundred year paper twenty gen men enemy general left
tho bo ho nnd aro ot ii ol la aud
people great country public con dr blood cure stomach health
states united president state mr
@jon_fitzgerald
Genre Assignments
@jon_fitzgerald
Classification Accuracy by Genre
Actual Genre Percent Right
advertisement 92.99325
news 87.48239
poetry 83.76231
prose 66.91618
@jon_fitzgerald
25 Clusters with Genre Probabilities
@jon_fitzgerald
25 Clusters with Genre Probabilities
WAGES IN 1800. The condition of the wages-class of that day may well be examined; it is full of instruction for social agitators. In the great cities unskilled workmen were hired by the day, bought their own food and found their own lodgings. But in the country, on the farms, or wherever a band was employed on some public work, they were fed and lodged by the employer and given a few dollars a month. On the Pennsylvania canals the diggers ate the coarsest diet, were housed in the rudest sheds, and paid $6 a month from May to November, and $5 a month from November to May.
@jon_fitzgerald
25 Clusters with Genre Probabilities
@jon_fitzgerald
25 Clusters with Genre Probabilities
@jon_fitzgerald
@jon_fitzgerald
Matthew Jockers, Macroanalysis
“…lead us not only to a deeper understanding of the genres…but also to clearer definitions of genre itself.”
@jon_fitzgerald
A HORSE’S PETITION TO HIS DRIVER.
Going up hill, whip me not. Coming down hill, hurry me not. On level tread, spare me not. Loose in stable, forget me not. Tired or hot, wash me not. If sick or old, chill me not. With bit and reins, Oh! jerk me not, And when you are angry, strike me not
@jon_fitzgerald
@jon_fitzgerald
Matthew Jockers & David Mimno, “Significant themes in 19th-century literature"
“The models we present here cannot represent the full meaning of individual books any more than satellite photos can show the details of individual trees. Like the satellite view, however, these macro-, or ‘distant-,’ scale perspectives on literature offer scholars a necessary context for and complement to closer readings.”
@jon_fitzgerald
Thank you.
@jon_fitzgerald