• Corpus ID: 18048854

Election Bias: Comparing Polls and Twitter in the 2016 U.S. Election

@article{Anuta2017ElectionBC,
  title={Election Bias: Comparing Polls and Twitter in the 2016 U.S. Election},
  author={David Anuta and Josh Churchin and Jiebo Luo},
  journal={ArXiv},
  year={2017},
  volume={abs/1701.06232}
}
While the polls have been the most trusted source for election predictions for decades, in the recent presidential election they were called inaccurate and biased. How inaccurate were the polls in this election and can social media beat the polls as an accurate election predictor? Polls from several news outlets and sentiment analysis on Twitter data were used, in conjunction with the results of the election, to answer this question and outline further research on the best method for predicting… 

Exploring the Effectiveness of Twitter at Polling the United States 2016 Presidential Election

The results show that when using tweet sentiment, the results obtain similar margins to polls conducted during the election period and come close to the actual popular vote outcome.

Social media for polling and predicting United States election outcome

This work creates a dataset consisting of approximately 3 million tweets ranging from September 22nd to November 8th, 2016 to explore the effectiveness of social media as a resource for both polling and predicting the election outcome.

A Longitudinal Study on Twitter-Based Forecasting of Five Dutch National Elections

An eight-year longitudinal study of predicting the outcome of elections based on party mentions in tweets found reasonably accurate predictions can be obtained that are under twice the error of the classic polls, but only after post-hoc optimization.

Location-Based Twitter Sentiment Analysis for Predicting the U.S. 2016 Presidential Election

The results show tweet sentiment mirrors the close races in the swing states; however, the differences in distribution of positive sentiment and volume between Clinton and Trump are not significant using the approach.

Modelling the Impact of Scandals: the case of the 2017 French Presidential Election

It is shown that scandals can lead to higher abstention at the election, as voters have no relevant candidate left to vote for.

Predicting Elections: Social Media Data and Techniques

This study aims to give an overview of the current state of approaches being utilized, social media used for data collection and the outcomes of the proposed approaches, either succeeded in making accurate electoral predictions using social media data and approaches used or not.

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.

A survey on political event analysis in Twitter

This short survey paper attempts to provide an overview of the most recent research works on the popular politics domain within the framework of the Twitter social network, by reviewing the Twittersphere from the computational social science point of view.

Sentiment Analysis of Twitter Data: Emotions Revealed Regarding Donald Trump during the 2015-16 Primary Debates

One of the key findings of this study is recognizing that negative or positive polarities in the tweets is not a good indicator to determine support for this candidate.

Prediction of USA November 2020 Election Results Using Multifactor Twitter Data Analysis Method

A new multifactor model for the election result prediction based on Twitter data has been developed and tested by attempting to predict the results of the US 2020 elections in November, which had not yet taken place when the first version of this article was written.

References

SHOWING 1-10 OF 10 REFERENCES

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

From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series

This work connects measures of public opinion measured from polls with sentiment measured from text, and finds that temporal smoothing is a critically important issue to support a suc- cessful model.

Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment

It is found that the mere number of messages mentioning a party reflects the election result, and joint mentions of two parties are in line with real world political ties and coalitions.

From the New York Times—

  • G. DeFriese
  • Psychology
    North Carolina medical journal
  • 2005
Children raised in families with stepmothers are likely to have less health care, less education and less money spent on their food than children raised by their biological mothers, three studies by

VADER: A Parsimonious Rulebased Model for Sentiment Analysis of Social Media Text

  • in International Conference on Weblogs and Social Media (ICWSM-14), (Ann Arbor, MI, United States,
  • 2014

2016 United States Presidential Election Tweet Ids

  • 2016

A Parsimonious Rule - based Model for Sentiment Analysis of Social Media Text

  • International Conference on Weblogs and Social Media ( ICWSM - 14 )
  • 2014

Latest Election Polls

  • Latest Election Polls
  • 2016

: A Parsimonious Rule - based Model for Sentiment Analysis of Social Media Text

  • International Conference on Weblogs and Social Media ( ICWSM - 14 )
  • 2014

State Poll UPI