Political preferences nowcasting with factor analysis and internet data: The 2012 and 2016 US presidential elections

Fabio Franch

Technological Forecasting and Social Change, 2021, vol. 166, issue C

Abstract: This work shows how Internet data can be aggregated to track political candidates’ performance during a presidential campaign. The ‘wisdom of crowds’ theory is here exploited to a fuller extent using a unique combination of data sources and methodology. This is first done by taking medium-level aggregations from applications such as BetFair, InTrade, PredictIt, Twitter, Facebook, MySpace, YouTube, Instagram, Google, FiveThirtyEight, and then by synthesizing via factor analysis a qualitative measure of popularity for both candidates, while controlling for the intensity of electoral discussions. For two different elections, the methodology extracts popularity functions that closely reflect popularity swings occurring during/shortly after the presidential debates and other campaign-related events. The model presents itself as a cheaper and more accurate alternative to electoral polling being based on aggregate, anonymous data and voter's actions; for the same reason, it has the potential to address the “Shy Trump Supporters” bias. The model outperforms political betting markets and established platforms such as RealClearPolitics, FiveThirtyEight and Twitter, in addition to the factor model's original variables.

Keywords: Election nowcasting; 2012 US presidential election; 2016 US presidential election; Wisdom of crowds; Factor analysis; Internet data (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0040162521000998
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:tefoso:v:166:y:2021:i:c:s0040162521000998

DOI: 10.1016/j.techfore.2021.120667

Access Statistics for this article

Technological Forecasting and Social Change is currently edited by Fred Phillips

More articles in Technological Forecasting and Social Change from Elsevier
Bibliographic data for series maintained by Catherine Liu ().