Friday, September 30, 2011

New research on Twitter teaches us about cross-cultural emotional patterns

Emerging research by Cornell University sociologists (set to be published in the journal, Science) tracks the mood of Twitter users over time. Analyzing a large corpus of tweets, the researchers found that patterns in mood follow a general rhythm across cultures and countries. The highlight of the study was published in an article in this week's New York Times:

"Drawing on messages posted by more than two million people in 84 countries, researchers discovered that the emotional tone of people’s messages followed a similar pattern not only through the day but also through the week and the changing seasons. The new analysis suggests that our moods are driven in part by a shared underlying biological rhythm that transcends culture and environment."

The study offers a true analysis of mood patterns using text analysis -- a growing area of interdisciplinary research that has computer scientists, social scientists, and communication researchers working collaboratively to understand large bodies of text -- from Tweets and blog posts to traditional news content. 

I might be a little bit biased, but one of my favorite pieces of research in this area was completed by colleagues in computer science at UW-Madison. The piece by Goldberg et al. (2009) analyzed a corpus of 100,000 New Year’s wishes uploaded to the Internet by individuals across the globe to coincide with the 2007 ball drop in Times Square. The most common wish topics according to the research -- peace, love, and health and happiness. This research represents just one of the many ways that text analysis can be applied to everyday language and discourse.

Participating as a "tweep" at the White House Twitter Town Hall this summer offered me not only the opportunity to meet Barack Obama and live tweet the event from the East Room, but also allowed me to attend a follow-up discussion about Twitter, social media, and data applications with Twitter CEO Jack Dorsey and top White House new media and technology officials. Let's just say that it's not just academics who understand the value of mining Twitter text data. 

As the reach of Twitter spreads (13% of US adults use Twitter according to a May 2011 report by the Pew Internet & American Life Project; with usage highest among Millennials, Gen Xers, and Blacks and Hispanics in particular) look for continued textual analysis of these precious tweets. 

No comments:

Post a Comment