Predicting the 2020 US Presidential Election with Twitter

TL;DR

This paper investigates using Twitter data for predicting the 2020 US Presidential Election, combining sentiment analysis and structural data, but finds limited success due to data scarcity and calls for further research.

Contribution

It introduces a new method integrating sentiment analysis and structural Twitter data with polling, aiming to improve electoral prediction models.

Findings

The proposed method underperformed compared to traditional polling.

Data scarcity limited the conclusiveness of the results.

Further research with more data is necessary for validation.

Abstract

One major sub-domain in the subject of polling public opinion with social media data is electoral prediction. Electoral prediction utilizing social media data potentially would significantly affect campaign strategies, complementing traditional polling methods and providing cheaper polling in real-time. First, this paper explores past successful methods from research for analysis and prediction of the 2020 US Presidential Election using Twitter data. Then, this research proposes a new method for electoral prediction which combines sentiment, from NLP on the text of tweets, and structural data with aggregate polling, a time series analysis, and a special focus on Twitter users critical to the election. Though this method performed worse than its baseline of polling predictions, it is inconclusive whether this is an accurate method for predicting elections due to scarcity of data. More research and more data are needed to accurately measure this method's overall effectiveness.