Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump

TL;DR

This study demonstrates that Twitter opinion trends closely match national polling data and can serve as an early indicator of public opinion shifts during the 2016 US Presidential Election.

Contribution

The paper introduces a novel method combining statistical physics and machine learning to accurately infer and predict public opinion from Twitter data.

Findings

Twitter trends align with NYT polling averages

Twitter opinion trends precede polls by 10 days

Twitter can be a cost-effective tool for social trend analysis

Abstract

Measuring and forecasting opinion trends from real-time social media is a long-standing goal of big-data analytics. Despite its importance, there has been no conclusive scientific evidence so far that social media activity can capture the opinion of the general population. Here we develop a method to infer the opinion of Twitter users regarding the candidates of the 2016 US Presidential Election by using a combination of statistical physics of complex networks and machine learning based on hashtags co-occurrence to develop an in-domain training set approaching 1 million tweets. We investigate the social networks formed by the interactions among millions of Twitter users and infer the support of each user to the presidential candidates. The resulting Twitter trends follow the New York Times National Polling Average, which represents an aggregate of hundreds of independent traditional polls, with remarkable accuracy. Moreover, the Twitter opinion trend precedes the aggregated NYT polls by 10 days, showing that Twitter can be an early signal of global opinion trends. Our analytics unleash the power of Twitter to uncover social trends from elections, brands to political movements, and at a fraction of the cost of national polls.