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

Abstract

Measuring and forecasting opinion trends from real-time social media is a long-standing goal of big-data analytics. Despite the large amount of work addressing this question, there has been no clear validation of online social media opinion trend with traditional surveys. Here we develop a method to infer the opinion of Twitter users by using a combination of statistical physics of complex networks and machine learning based on hashtags co-occurrence to build an in-domain training set of the order of a million tweets. We validate our method in the context of 2016 US Presidential Election by comparing the Twitter opinion trend with the New York Times National Polling Average, representing an aggregate of hundreds of independent traditional polls. The Twitter opinion trend follows the aggregated NYT polls with remarkable accuracy. We investigate the dynamics of the social network formed by the interactions among millions of Twitter supporters and infer the support of each user to the presidential candidates. 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 traditional surveys.

Influence of fake news in Twitter during the 2016 US presidential election

“…A majority of users, 64%, is in favor of Hillary Clinton while 28% is in favor of Donald Trump (8% are unclassified as they have the same number of tweets in each camp). However, we find that Trump supporters are, in average, 1.5 times more active than Clinton supporters [27]. The supporters therefore represent the general Twitter population commenting on the candidate of the election.…”

“…We find two different mechanisms for the dynamics of fake news and traditional news. The top spreaders of center and left leaning news outlets, who are mainly journalists, are the main drivers of Twitter's activity and in particular of Clinton supporters' activity, who represent the majority in Twitter [27]. For fake news, we find that it is the activity of Trump supporters that governs their dynamics and top spreaders of fake news are merely following it.…”

“…The full detail of our method and the validation of its opinion trend with the national polling average of the New York Times is described in ref. [27]. We use our full dataset of tweets concerning the two candidates, namely 171 million tweets sent by 11 million distinct users during more than five months.…”

“…Here, we use a dataset of 171 million tweets sent by 11 million users covering almost the whole activity of users regarding the two main US presidential candidates, Hillary Clinton and Donald Trump, collected during the five months preceding election day and used to extract and analyze Twitter opinion trend in our previous work [27]. We compare the spread of news coming from websites that have been described as displaying fake news with the spread of news coming from traditional, fact-based, news outlets with different political orientations.…”

Extracting significant signal of news consumption from social networks: the case of Twitter in Italian political elections

“…Different studies analyzed the raising of grass-root democratic protests as Arab springs [5], Occupy Wall Street [6] or the Spanish "Indignados" [7]. Analogously, the dynamics of the electoral campaign online media has a (relatively) long literature, focusing, time by time, on USA [8][9][10][11][12][13][14], Australia [15,16], Norway [17], Spain [18], Italy [19][20][21], France [22] and UK [23,24]. Generally, the shift from mediated to disintermediated news consumption has led to a range of documented phenomena: users tend to focus on information reinforcing their opinion (confirmation bias [25][26][27][28][29]) and to group in clusters of people with similar viewpoints, forming the so called echo chambers [26][27][28][29][30][31].…”