Generations vs. contexts

When I first thought about using digital texts to track shifts in language usage over time, the largest reliable repository of e-texts was Project Gutenberg. I quickly found out, though, that they didn't have works for years, somewhat to my surprise. (It's remarkable how much metadata holds this sort of work back, rather than data itself). They did, though, have one kind of year information: author birth dates. You can use those to create same type of charts of word use over time that people like me, the Victorian Books project, or the Culturomists have been doing, but in a different dimension: we can see how all the authors born in a year use language rather than looking at how books published in a year use language.

I've been using 'evolution' as my test phrase for a while now: but as you'll see, it turns out to be a really interesting word for this kind of analysis. Maybe that's just chance, but I think it might be a sort of indicative test case--generational shifts are particularly important for live intellectual issues, perhaps, compared to overall linguistic drift.

To start off, here's a chart of the usage of the word "evolution" by share of words per year. There's nothing new here yet, so this is merely a reminder:

 

Here's what's new: we can also plot by year of author birth, which shows some interesting (if small) differences:

Graphing word trends inside genres

Genre information is important and interesting. Using the smaller of my two book databases, I can get some pretty good genre information about some fields I'm interested in for my dissertation by using the Library of Congress classifications for the books. I'm going to start with the difference between psychology and philosophy. I've already got some more interesting stuff than these basic charts, but I think a constrained comparison like this should be somewhat more clear.

Most people know that psychology emerged out of philosophy, becoming a more scientific or experimental study of the mind sometime in the second half of the 19C. The process of discipline formation is interesting, well studied, and clearly connected to the vocabulary used. Given that, there should be something for lexical statistics in it. Also, there's something neatly meta about using the split of a 'scientific' discipline off of a humanities one, since some rhetoric in or around the digital humanities promises a bit more rigor in our analysis by using numbers. So what are the actual differences we can find?

Let me start by just introducing these charts with a simple one. How much do the two fields talk about "truth?"

 

Cluster Charts

I'll end my unannounced hiatus by posting several charts that show the limits of the search-term clustering I talked about last week before I respond to a couple things that caught my interest in the last week.

To quickly recap: I take a word or phrase—evolution, for example—and then find words that appear disproportionately often, according to TF-IDF scores, in the books that use evolution the most. (I just use an arbitrary cap to choose those books--it's 60 books for these charts here. I don't think that's the best possible implementation, but given my processing power it's not terrible). Then I take each of those words, and find words that appear disproportionately in the books that use both evolution and the target word most frequently. This process can be iterated any number of times as we learn about more words that appear frequently—"evolution"–"sociology" comes out of the first batch, but it might suggest "evolution"–"Hegel" for the second, and that in turn might suggest "evolution" –"Kant" for the third. (I'm using colors to indicate at what point in the search process a word turned up: Red for words that associated with the original word on its own, down to light blue for ones that turned up only in the later stages of searching).

Often, I'll get the same results for several different search terms—that's what I'm relying on. I use a force-directed placement algorithm to put the words into a chart based on their connections to other words. Essentially, I create a social network where a term like "social" is friends with "ethical" because "social" is one of the most distinguishing terms in books that score highly on a search for "evolution"–"social", and "ethical" is one of the most distinguishing terms in books that score highly on a search for "evolution"–"ethical". (The algorithm is actually a little more complicated than that, thought maybe not for the better). So for evolution, the chart looks like this. (click-enlarge)

 

Clustering from Search

Because of my primitive search engine, I've been thinking about some of the ways we can better use search data to a) interpret historical data, and b) improve our understanding of what goes on when we search. As I was saying then, there are two things that search engines let us do that we usually don't get:

1)  Numeric scores on results
2) The ability to from a set of books to a set of high-scoring words, as well as (the normal direction) from a set of words to a set of high-scoring books.

We can start to do some really interesting stuff by feeding this information back in and out of the system. (Given unlimited memory, we could probably do it all even better with pure matrix manipulation, and I'm sure there are creative in-between solutions). Let me give an example that will lead to ever-elaborating graphics.

An example: we can find the most distinguishing words for the 100 books that use “evolution” the most frequently: 

Searching for Correlations

More access to the connections between words makes it possible to separate word-use from language. This is one of the reasons that we need access to analyzed texts to do any real digital history. I'm thinking through ways to use patterns of correlations across books as a way to start thinking about how connections between words and concepts change over time, just as word count data can tell us something (fuzzy, but something) about the general prominence of a term. This post is about how the search algorithm I've been working with can help improve this sort of search. I'll get back to evolution (which I talked about in my post introducing these correlation charts) in a day or two, but let me start with an even more basic question that illustrates some of the possibilities and limitations of this analysis: What was the Civil War fought about?

I've always liked this one, since it's one of those historiographical questions that still rattles through politics. The literature, if I remember generals properly (the big work is David Blight, but in the broad outline it comes out of the self-situations of Foner and McPherson, and originally really out of Du Bois), says that the war was viewed as deeply tied to slavery at the time—certainly by emancipation in 1863, and even before. But as part of the process of sectional reconciliation after Reconstruction (ending in 1876) and even more into the beginning of Jim Crow (1890s-ish) was a gradual suppression of that truth in favor of a narrative about the war as a great national tragedy in which the North was an aggressor, and in which the South was defending states' rights but not necessarily slavery. The mainstream historiography has since swung back to slavery as the heart of the matter, but there are obviously plenty of people interested in defending the Lost Cause. Anyhow: let's try to get a demonstration of that. Here's a first chart:

 

How should we read this kind of chart? Well, it's not as definitive as I'd like, but there's a big peak the year after the war breaks out in 1861, and a massive plunge downwards right after the disputed Hayes–Tilden election of 1876. But the correlation is perhaps higher than the literature would suggest around 1900. And both the ends are suspicious. In the 1830s, what is a search for "civil war" picking up? And why is that dip in the 1910s so suspiciously aligned with the Great War? Luckily, we can do better than this.

Call numbers

I finally got some call numbers. Not for everything, but for a better portion than I thought I would: about 7,600 records, or c. 30% of my books.

The HathiTrust Bibliographic API is great. What a resource. There are a few odd tricks I had to put in to account for their integrating various catalogs together (Michigan call numbers are filed under MARC 050 (Library of Congress catalog), while California ones are filed under MARC 090 (local catalog), for instance, although they both seem to be basically an LCC scheme). But the openness is fantastic--you just plug in OCLC or LCCN identifiers into a url string to get an xml record. It's possible to get a lot of OCLCs, in particular, by scraping Internet Archive pages. I haven't yet found a good way to go the opposite direction, though: from a large number of specially chosen Hathi catalogue items to IA books.

This lets me get a slightly better grasp on what I have. First, a list of how many books I have for each headline LC letter:

Now with actual text!

Lexical analysis widens the hermeneutic circle. The statistics need to be kept close to the text to keep any work sufficiently under the researcher's control. I've noticed that when I ask the computer to do too much work for me in identifying patterns, outliers, and so on, it frequently responds with mistakes in the data set, not with real historical data. So as I start to harness this new database, one of the big questions is how to integrate what the researcher already knows into the patterns he or she is analyzing.


This is all by way of showing off the latest thing it lets me do--get examples of actual usage so we can do semantic processing ourselves, rather than trying to have a computer do it poorly. It might be good to put some tests like this into the code by default, as a check on interpretive hubris. I need to put the years and titles in here too, but if we just take a random set of samples of the language of natural selection, I think it's already clear that we get an interesting new form of text to interpret; it's sort of like reading the usage examples in the OED, except that we can create much more interesting search contraints on where our passages come from.


> get.usage.example("natural selection",sample(books,1))
[1] "we might extend the parallel and get some good illustrations of natural selection from the history of architecture and the origin of the different styles under different climates and conditions"

Comparing usage patterns across the isms

What can we do with this information we’ve gathered about unexpected occurrences? The most obvious thing is simply to look at what words appear most often with other ones. We can do this for any ism given the data I’ve gathered. Hank asked earlier in the comments about the difference between "Darwinism" and evolutionism, so:

> find.related.words("darwinism",matrix = "percent.diff", return=5)
phenomenism evolutionism revolutionism subjectivism hermaphroditism
2595.147 1967.021 1922.339 1706.679 1681.792


Phenomenism appears 2,595%—26 times—more often in books about Darwin than chance would imply. That revolutionism is so high is certainly interesting, and maybe there’s some story out there about why hermaphroditism is so high. The takeaway might be that Darwinism appears as much in philosophical literature as scientific, which isn’t surprising.

But we don’t just have individual counts for words—we have a network of interrelated meanings that lets us compare the relations across all the interrelations among words. We can use that to create a somewhat different list of words related to Darwinism:

Isms and ists

Hank asked for a couple of charts in the comments, so I thought I'd oblige. Since I'm starting to feel they're better at tracking the permeation of concepts, we'll use appearances per 1000 books as the y axis:

And Darwin after the break.

Back to Darwin

Henry asks in the comments whether the decline in evolutionary thought in the 1890s is the "'Eclipse of Darwinism,' rise or prominence of neo-Lamarckians and saltationism and kooky discussions of hereditary mechanisms?" Let's take a look, with our new and improved data (and better charts, too, compared to earlier in the week--any suggestions on design?). First,three words very closely tied to the theory of natural selection.

Three rises from around 1859, Origin's publication date (obviously the numbers for Spencer are inflated by other Spencers in the world, but the trend seems like it might be driven by Herbert); and three peaks at different points from 1885 to 1900, followed by a fall and perhaps a recovery. The question is: how significant are those falls, and how can we interpret them? First, let's look at the bookcounts: are those falls a result of less intensive discussion of the subjects, or of a waning in interest across all books?

Diffusion patterns for news and technological events

An anonymous correspondent says:

You mention in the post about evolution & efficiency that "Offhand, the evolution curve looks more the ones I see for technologies, while the efficiency curve resembles news events."

That's a very interesting observation, and possibly a very important one if it's original to you, and can be substantiated. Do you have an example of a tech vs news event graph? Something like lightbulbs or batteris vs the Spanish American war might provide a good test case.

Also, do you think there might be changes in how these graphs play out over a century? That is, do news events remain separate from tech stuff? Tech changes these days are often news events themselves, and distributed similarly across media.

I think another way to put the tech vs news event could be in terms of the kind of event it is: structural change vs superficial, mid-range event vs short-term.

Anyhow, a very interesting idea, of using the visual pattern to recognize and characterize a change. While I think your emphasis on the teaching angle (rather than research) is spot on, this could be one application of these techniques where it'd be more useful in research.

He or she is right that technology vs. news isn't quite the right way to describe it. Even in the 19C, some technology changes are news events, while others aren't. But let's look at some examples here.