Predicting the 2014 Academy Awards Using Twitter
Simon Munzert, Christian Rubba, Peter Meißner, Dominic Nyhuis · 2014
Social media and the social network Twitter, in particular, have attracted the curiosity of scientists from various disciplines. The fact that millions of people regularly interact with the world by tweeting provides invaluable insight into people's feelings, attitudes, and behavior. Twitter data have been used as a prediction tool for elections, spread of influenza, movie sales, or the stock market. This chapter presents a case study to predict the winners of the 2014 Academy Awards using the tweets in the days prior to the event. Specifically, it tries to predict the results of three awards—best picture, best actress, and best actor. The chapter elaborates the data collection by introducing the Twitter APIs and the specific setup used to gather the tweets. It talks about the streamR and twitteR packages that help connecting the two main access points for current and retrospective data collection.