Tweet One for the Books
Yesterday morning, National Public Radio's Morning Edition carried an interesting story about how technologists are working on new translation technology that not only can read languages of the Middle East, but can "read between the tweets" and understand the nuances in some of the social media conversation in order to better analyze and predict what is going to happen next in the region.
Computer scientist Rohini Srihari says existing computer translators for Urdu are often too literal.
"What I want is to determine who are the people, places and things being talked about," she says. "Is there an opinion being expressed? Is it a positive or negative opinion being expressed?"
Srihari is working on a natural language program that can determine the tone as well as the facts.
"So in Twitter posts and tweets and so on, if there's specific factual information that's being mentioned — they want that extracted," Srihari says. "There's also definitely an interest in sentiment and opinion mining."
Also quoted in the report is Ernest Tucker, a history professor with the Center for Middle East and Islamic Studies at the U.S. Naval Academy, who "argues that history is best told not by what the Napoleans say, but by the foot soldiers, or, in this case, the tweeters."
It reminded me of my favorite college history course at Temple University -- History from the Bottom Up, which looked at events in American History from the letters and diaries of ordinary citizens of the time rather than from the wealthy and powerful elite, who typically create and record our historical events.
It was interesting to think about Twitter as being a harbinger of social moods, especially considering the amount of promotion and commerce that currently constitutes much of the tweeting. However, it does provide a snapshot of a wide variety of people's instant reactions to current events and, in that respect, is a fascinating temperature read for a local, regional and even national viewpoint. As the research continues, it will of course be important to determine if this medium truly represents a wide-ranging viewpoint that encompasses all demographics and income levels. And it will need to factor out the people who are, in some way, compensated for tweeting certain topics. At that point, I might be willing to consider Twitter as part of a new approach to recording History from the Bottom Up.