Measuring and Understanding Opinion Trends in Twitter
In our manuscript, we develop an new method to infer the opinion of Twitter 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. In the context of the 2016 US presidential election, we validate our Twitter opinion trend with the New York Times National Polling Average. We show that our Twitter opinion trend can predict the value of the polls up to 10 days in advance with a better accuracy then a linear extrapolation of the polls. Finally, we show that the difference in behavior and activity between the supporters of the two candidates results in the fact that Twitters opinion mainly measures the engagement of Clinton supporters.