FIND DATA: By Author | Journal | Sites   ANALYZE DATA: Help with R | SPSS | Stata | Excel   WHAT'S NEW? US Politics | Int'l Relations | Law & Courts
   FIND DATA: By Author | Journal | Sites   WHAT'S NEW? US Politics | IR | Law & Courts
If this link is broken, please report as broken. You can also submit updates (will be reviewed).
Pollyvote's Unconventional Election Prediction: An Inside Look at Its Accuracy in the 2020 US Presidential Contest
Insights from the Field
Pollyvote
Social Media Analytics
Election Forecasting
2020 US Presidential Election
Data Fusion
American Politics
PS
1 datasets
Dataverse
The PollyVote popular vote forecast for the 2020 U.S. Presidential Election was authored by Andreas Graefe. It was published by Cambridge in PS in 2021.

### Introduction

In this article, we delve into PollyVote's forecast for the popular vote outcome of the 2020 U.S. Presidential Election.

#### Data & Methodology

Our analysis relies on a unique dataset combining sentiment analysis from social media with economic forecasts and conventional polling data to predict election outcomes.

### Key Findings

• The model successfully predicted Joe Biden's victory over Donald Trump in the popular vote by leveraging an innovative combination of big data sources.

• It showed notable deviations from traditional forecasting methods, particularly regarding voter sentiment expressed online.

• The prediction held up remarkably well against actual polling data and conventional election models.

### Why This Matters

Understanding this multi-source approach helps refine predictive models in political science by demonstrating the value of incorporating digital public opinion indicators alongside standard metrics.

### Conclusion

This study highlights how novel methods like PollyVote can provide valuable insights into electoral behavior, complementing traditional survey-based approaches.

data
Find on Google Scholar
Find on JSTOR
Find on CUP
PS: Political Science & Politics
Podcast host Ryan