Mapping Emotions Through a Century

(image courtesy of http://www.behance.net/gallery/Migration-and-Identity/1335529 )
(image courtesy of http://www.behance.net/gallery/Migration-and-Identity/1335529 )

An NPR news story discusses how researchers at Bristol used sentiment analysis techniques on a massive corpus of digitised texts to produce a “map of human emotion through the century”.  The resulting trends demonstrate clear peaks in the 20’s (happiness) and troughs in the 1940’s, and they discuss how the use of books (as opposed to other kinds of texts, including personal correspondence, news media, etc) served essentially as a filter of public opinion

http://www.npr.org/blogs/health/2013/04/01/175584297/mining-books-to-map-emotions-through-a-century

Extrapolating from this story, what if we were to use digital archives of the Internet over the past 3 decades to build such a map?  Google would probably be the best equipped for the job, but even Google wasn’t around at the very earliest stages.  Given the now massive volumes of digital text produced by every single person using the Web, would such a chronology even be feasible?

Advertisements

Leave a Reply

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

WordPress.com Logo

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

Google+ photo

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

Twitter picture

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

Facebook photo

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

Connecting to %s