Twitter data has been considered very important for advertisers, the company itself, and also for the government. Tweets from users already help the government identify individual threats like someone talking about overthrowing the government. But social media has the potential to give the government much more insight into the collective desires of the masses.
Twitter history more relevant than personal history
A new study from Arizona State University, Texas A&M, and Yahoo found that, using the right algorithm, the chances of any Twitter user posting something in protest can be predicted with 70% accuracy. Such information can be applied to the real world to predict a protest movement and how big the protest will eventually get. The government is surely interested in such studies as the Office of Naval Research also funded this research.
For the study, researchers considered 2,686 posts related to the Nigerian general election, which took place between February and April 2015. The elections, which were marred by the insurgency of the Boko Haram, faced accusations of voting irregularities. To predict if someone might start protesting on Twitter, studying his or her Twitter history of interacting with other people who are part of the movement is much more relevant than their personal history.
Jim O’Shaughnessy: Fear Signals Created By The Reptilian Brain
ValueWalk's Raul Panganiban interviews Jim O’Shaughnessy, Chairman, Co-chief Investment Officer, and Portfolio Manager at O’Shaughnessy Asset Management. In this part, Jim discusses the fear and emotional signals created by the reptilian brain. Q1 2020 hedge fund letters, conferences and more That's very cool. For the factor to try to seek the reason why it works, Read More
Brownian motion theory used
In an email to Defense One, researchers Suhas Ranganath and Fred Morstatter, said, “The interaction we study is how users mention each other.”
And in their model, the chances “of the future post expressing protest increases” if the post mentioning the user is anyway related to the protest or the post suggests the user is interested in the protest.
“We dynamically learn [or teach] the model by testing how each of the previous status messages of the given user are affected by the recent posts mentioning him. We then use the model to predict the likelihood of the user expressing protest in his next post,” the email read.
Researchers used the Brownian motion theory to come up with the formula. This theory is primarily used to track particle movement or model fluctuations in the stock market.
“Brownian Motion for fluid particles models change in the direction of the particle movement on collision with other particles,” Suhas told Defense One.
In the study, each “particle” is taken as a social media user. So collisions with other particles that relate to other users mentioning him or her and a change in direction relate to the “user’s inclination to express protest in his next post.”