I’m currently working with one of our best students on a Capstone project that asks the following question: “Is there a form of social media that, properly analyzed, could be used to predict the outcome of the 2012 Presidential election?” After consulting with a polling expert at Wesleyan University, we came to the conclusion that it was possible to use social media based on polling theories, but that we would be in uncharted waters. This Professor suspected there was a chance that Twitter might be used to forecast a national election outcome, based on the assumption that Twitter had become a reliable gauge of public sentiment in some circles. My student immediately searched for similar studies and uncovered the following:

Image representing Twitter as depicted in Crun...

Image via CrunchBase

1. The CIA has an  entire division that does nothing but look at public data for the purpose of characterizing the mood of a nation or group: “The intelligence analysts at the agency’s Open Source Center, who other agents refer to as ‘vengeful librarians,’ are tasked with sifting through millions of tweets, Facebook messages, online chat logs, and other public data on the World Wide Web to glean insights into the collective moods of regions or groups abroad.” (The Atlantic Monthly – Jared Keller)

2. Analysis of Twitter feeds have already been used to predict the behavior of the stock market, perhaps an even more fickle index than public sentiment: “Here we investigate whether measurements of collective mood states derived from large-scale Twitter feeds are correlated to the value of the Dow Jones Industrial Average (DJIA) over time… we find an accuracy of 87.6% in predicting the daily up and down changes in the closing values of the DJIA.” (study completed at Indiana University)

I love this project because it combines rigorous analysis of political trends and a study of Twitter as a predictive rather than reflective social networking tool (what some have called “crowdsourcing”). Suppose we could ascertain the ongoing sentiment of our students through a review of an appropriate Twitter feed?  Love to hear your feedback.


Enhanced by Zemanta
Advertisements