Nowcasting with social media data

Abstract

Social media is a source of real time data that individuals create and voluntarily share on major social media generators such as Facebook, Twitter, Google, Yahoo, and Instagram. Nowcasting uses real-time data and is defined as the prediction of the present, the very near future, and the very recent past. Nowcasting with social media assists businesses and government agencies in understanding public opinion and trends, and in creating timely forecasts of economic indicators. The example includes geo-economic events: how the public's sentiment affects the stock market [1], predicting political alignment: management of political strategy [4], and social questions: popular events associated with increased public sentiment [8]. Nowcasting and social media are also being used together to discover unusual social events such as demonstrations and spontaneous festivals, and natural disasters such as earthquakes and storms [6], and to forecast early detection of disease activity — thereby allowing rapid disease response, which reduces the public impact of disease [2].