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

@article{Bovet2018ValidationOT,
  title={Validation of Twitter opinion trends with national polling aggregates: Hillary Clinton vs Donald Trump},
  author={Alexandre Bovet and F. Morone and Hern{\'a}n A. Makse},
  journal={Scientific Reports},
  year={2018},
  volume={8}
}
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… 

The role of bot squads in the political propaganda on Twitter

The authors take a complex networks approach to study the Twitter debate around the Italian migrant crisis, finding evidence for "bots squads” amplifying the tweets of a few key political figures.

Did State-sponsored Trolls Shape the US Presidential Election Discourse? Quantifying Influence on Twitter

This work quantifies the influence of troll accounts on Twitter by analyzing 152.5 million tweets from 9.9 million users, and provides a global influence ranking of all Twitter accounts and finds that only four troll accounts appear in the top-1000 and only one in thetop-100.

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

The analysis of the directed network of validated retweets reveals signals of the alliances formed after the elections, highlighting commonalities of interests before the event of the national elections.

Can We Forecast Presidential Election Using Twitter Data? An Integrative Modelling Approach

This study draws on political science prediction models and modifies them in two aspects and uses Twitter sentiment to replace polling data, and transforms traditional political science models from the national level to the county level, the finest spatial level of voting counts.

Finding Trustworthy Users: Twitter Sentiment Towards US Presidential Candidates in 2016 and 2020

This paper proposes a novel method to forecast the U.S. presidential election in 2016 post facto and make predictions for the 2020 election by taking an individual’s trustworthiness, participation bias and the participation bias into account.

Predicting Brazilian and U.S. Elections with Machine Learning and Social Media Data

  • K. BritoP. Adeodato
  • Computer Science
    2020 International Joint Conference on Neural Networks (IJCNN)
  • 2020
This work proposes a novel approach to training ML models for predicting vote share based on modeling and using social media data gathered from the posts of official candidates’ profiles combined with traditional polls and uses an artificial neural network for prediction.

Topology comparison of Twitter diffusion networks effectively reveals misleading information

The results highlight that the communities of users spreading mainstream news, compared to those sharing misleading news, tend to shape diffusion networks with subtle yet systematic differences which might be effectively employed to identify misleading and harmful information.

Topology comparison of Twitter diffusion networks reliably reveals disinformation news.

The results highlight that the communities of users spreading mainstream rather than disinformation news tend to shape diffusion networks with subtle yet systematic differences, which opens the way to promptly and correctly identifying disinformation on social media by solely inspecting the resulting diffusion networks.

Quantifying the structure of controversial discussions with unsupervised methods: a look into the Twitter climate change conversation

It is observed that, while the echo chamber structures are consistent throughout the year, most users inside the echo chambers change from one week to the next, suggesting that they are a stable emergent property of the Twittersphere.

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

It is found that, while top influencers spreading traditional center and left leaning news largely influence the activity of Clinton supporters, this causality is reversed for the fake news: the activityof Trump supporters influences the dynamics of the top fake news spreaders.
...

References

SHOWING 1-10 OF 72 REFERENCES

Digital Trace Data in the Study of Public Opinion

In this article, we examine the relationship between metrics documenting politics-related Twitter activity with election results and trends in opinion polls. Various studies have proposed the

Towards Passive Political Opinion Polling using Twitter

The automated senti- ment analysis of tweets from UK Members of Parliament (MPs) towards the main political parties is investigated and the volume and sentiment of the tweets from other users are investigated as a proxy for their voting intention and the results are compared against existing poll data.

Characterizing and modeling an electoral campaign in the context of Twitter: 2011 Spanish Presidential Election as a case study

The user activity in the online social network Twitter is analyzed, during the 2011 Spanish Presidential electoral process, and it is found that such activity is correlated with the election results, and a network growth model is developed to reproduce the interactions taking place among politicians.

The Effects of Twitter Sentiment on Stock Price Returns

Investigating the relations between a well-known micro-blogging platform Twitter and financial markets shows that sentiment polarity of Twitter peaks implies the direction of cumulative abnormal returns.

Predicting and Interpolating State‐Level Polls Using Twitter Textual Data

This article combines 1,200 state-level polls during the 2012 presidential campaign with over 100 million state-located political tweets; models the polls as a function of the Twitter text using a new linear regularization feature-selection method; and shows that when properly modeled, the Twitter-based measures track and to some degree predict opinion polls.

Online Human-Bot Interactions: Detection, Estimation, and Characterization

This work presents a framework to detect social bots on Twitter, and describes several subclasses of accounts, including spammers, self promoters, and accounts that post content from connected applications.

Predicting US Primary Elections with Twitter

Using social media for political analysis is becoming a common practice, especially during election time. Many researchers and media are trying to use social media to understand the public opinion

Twitter, Public Opinion, and the 2011 Nigerian Presidential Election

It was found that counts of the mentions on Twitter of the two major candidates correlated strongly with polling and election results when compared across the country's geopolitical regions, though the same data over represented two other candidates who did not fare as well in the polls or at the ballot box.

Predicting Elections for Multiple Countries Using Twitter and Polls

The authors treat this task as a multivariate time-series forecast, extracting Twitter- and poll-based features and training different predictive algorithms, achieving better results than several past works and the commercial baseline.

Election Forecasts With Twitter

This study investigates whether microblogging messages on Twitter validly mirror the political landscape off-line and can be used to predict election results. In the context of the 2009 German
...