Algorithms & Echo Chambers: Can Twitter Predict an Election?

Kiya Bhayani


Supervised by Stuart M Allen; Moderated by Irena Spasic

Twitter has transformed the way individuals communicate and share information. Politics is one area where it has had a significant influence, becoming a tool for political campaigns, political analysts, and voters to express themselves, mobilise supporters, and obtain real-time information.

This study aims to look at the relationship between Twitter sentiment and election polling data, specifically whether Twitter sentiment can be utilised to forecast election outcomes accurately. The study implemented and evaluated six different sentiment analysis methods to determine the best method for tweet classification. Once selected, the process was applied to six recent national elections in the United States and the United Kingdom, examining two at an event level.

The results of this study indicate that whilst Twitter sentiment can be used to get a real-time response to specific events, it is too volatile to be used to track voter intention in the same manner as polling. The study's findings emphasise the importance of combining traditional polling methodologies with social media analysis to achieve a more comprehensive knowledge of political trends and voter behaviour.

Initial Plan (03/02/2023) [Zip Archive]

Final Report (19/05/2023) [Zip Archive]

Publication Form