So what’s text analysis actually good for?

13 07 2014

If you asked me to identify the most important difference between social-scientific research circa 2004 and 2014, I would be tempted to point to the rise of quantitative discourse analysis. The quantity and quality of text analysis being done by social scientists has increased dramatically in the last decade. What this means is that getting a PhD in a field like history is now rather different than it was in 2000-5, when I did mine.  This video gives a sense of what cutting-edge historical research now looks like.

Now I have very mixed feelings about the rise of digital humanities. Some of the Digital Humanities projects I have seen tell us nothing new despite the use of the sexy new technologies. Such projects are a huge waste of time and money. Then there are the Digital Humanities projects that make a genuine but modest contribution to their fields. Some of the research done using the new techniques,  expands our understanding somewhat, but I don’t think that it will dramatically change our view of the subject.  

Then there is research with really revolutionary potential. Here’s an example of that. In modern societies, people tend to distinguish violent crimes from “mere” property crimes and demand much more severe penalties for the former. In backward societies such as Saudi Arabia, the priorities are reversed and there are severe penalties for the theft of even small amounts, while some forms of severe violence go unpunished. This raises the historical question of when exactly the modern Western distinction between violent and property crimes emerged and became widespread in Western societies. 

A new Digital Humanities project,  The civilizing process in London’s Old Bailey, answer this question.






The jury trial is a critical point where the state and its citizens come together to define the limits of acceptable behavior. Here we present a large-scale quantitative analysis of trial transcripts from the Old Bailey that reveal a major transition in the nature of this defining moment.

…we demonstrate the emergence of semantically distinct violent and nonviolent trial genres. We show that although in the late 18th century the semantic content of trials for violent offenses is functionally indistinguishable from that for nonviolent ones, a long-term, secular trend drives the system toward increasingly clear distinctions between violent and nonviolent acts.

…This work provides a new window onto the cultural and institutional changes that accompany the monopolization of violence by the state, described in qualitative historical analysis as the civilizing process.

new PNAS paper by Klingenstein, Hitchcock, and DeDeo.


H/T to Chris Blattman. 



Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: