Politics and Big Data ─ Nowcasting and Forecasting Elections With Social Media

The importance of social media as a way to monitor an electoral campaign is well established. Day-by-day, hour-by-hour evaluation of the evolution of online ideas and opinion allows observers and scholars to and monitor trends and momentum in public opinion well before traditional polls. However, there are difficulties in recording and analyzing often brief, unverified comments while the unequal age, gender, social and racial representation among social media users can produce inaccurate forecasts of final polls. Reviewing the different techniques employed using social media to nowcast and forecast elections this book assesses its achievements and limitations while presenting a new technique of ‘Sentiment Analysis’ to improve upon them. The authors carry out a meta-analysis of the existing literature to show the conditions under which social media-based electoral forecasts prove most accurate while new case studies from France, Italy and the United States demonstrate how much more accurate ‘Sentiment Analysis’ can prove.

Andrea Ceron is Assistant professor at UniversitA degli Studi di Milano where he teaches Political and Administrative Systems, and Applied Multivariate Analysis for Social Scientists. His research focuses on intra-party politics, quantitative text analysis, media bias, and social media analysis. He has published a dozen of papers in international academic peer-reviewed journals like British Journal of Political Science, European Journal of Political Research, Party Politics, New Media & Society, Electoral Studies, Social Science Computer Review, Journal of Language and Politics, and others. Luigi Curini is Associate professor of political science at UniversitA degli studi di Milano (Italy) where he teaches Political Science, Applied Multivariate Analysis for Social Scientists, Game Theory, and Analysis of Political Institutions. His research focuses on party competition, spatial theory of voting, and social media analysis. He has published over 30 papers in international academic peer-reviewed journals like Comparative Political Studies, Journal of Politics, British Journal of Political Science, European Journal of Political Research, Public Choice, Party Politics, European Political Science Review and many others. Stefano Maria Iacus is Associate professor of mathematical statistics and probability at UniversitA degli Studi di Milano. Member of the R Core Team for the deveolpment of the R statistical software. His fields of interest include computational statistics, theoretical statistics, inference for stochastic processes, text mining and sentiment analysis, and causal inference. He has published over 50 papers in international academic peer-reviewed journals.