SOR researcher Nelly Litvak has acquired a Google Award for her research: Mathematics for trend detection in social media.
Important trends, events, political and social activities, are often initiated on-line before they materialize in our daily off-line world. Social media played a key role in Arab Spring, Anti-FARC social movement in Colombia, and Russian protests in 2011. The goal of this project is to provide efficient and consistent statistical methods for early detection of trends and activities in social media. This is done through evaluations of the dynamic dependencies between the agents in social media: their number of connections, number of posts, number of mentions, amount of time spend on the social media platform, geographical location, past activities, etc. A clear distinction of this work is in mathematically justified probabilistic and statistical approach, based on rank correlations, suitable for dealing with highly skewed distributions. An essential part of this project is to create an open source data set of the social media showing a prominent dynamics, with the impact on off-line events.
The award is a student fellowship for a year, to work on this specific topic.