Using Facebook data to predict the 2016 U.S. presidential election
Open Access
- 1 December 2021
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 16 (12), e0253560
- https://doi.org/10.1371/journal.pone.0253560
Abstract
We use 19 billion likes on the posts of top 2000 U.S. fan pages on Facebook from 2015 to 2016 to measure the dynamic ideological positions for politicians, news outlets, and users at the national and state levels. We then use these measures to derive support rates for 2016 presidential candidates in all 50 states, to predict the election, and to compare them with state-level polls and actual vote shares. We find that: (1) Assuming that users vote for candidates closer to their own ideological positions, support rates calculated using Facebook predict that Trump will win the electoral college vote while Clinton will win the popular vote. (2) State-level Facebook support rates track state-level polling averages and pass the cointegration test, showing two time series share similar trends. (3) Compared with actual vote shares, polls generally have smaller margin of errors, but polls also often overestimate Clinton’s support in right-leaning states. Overall, we provide a method to forecast elections at low cost, in real time, and based on passively revealed preference and little researcher discretion.This publication has 15 references indexed in Scilit:
- Quantifying Social Media’s Political Space: Estimating Ideology from Publicly Revealed Preferences on FacebookAmerican Political Science Review, 2015
- Birds of the Same Feather Tweet Together: Bayesian Ideal Point Estimation Using Twitter DataPolitical Analysis, 2015
- Mapping the Ideological MarketplaceAmerican Journal of Political Science, 2013
- Multi-cycle forecasting of congressional elections with social mediaPublished by Association for Computing Machinery (ACM) ,2013
- Ideological Segregation Online and Offline *The Quarterly Journal of Economics, 2011
- What Drives Media Slant? Evidence From U.S. Daily NewspapersEconometrica, 2010
- A Measure of Media BiasThe Quarterly Journal of Economics, 2005
- The Statistical Analysis of Roll Call DataAmerican Political Science Review, 2004
- Linear Probability Models of the Demand for Attributes with an Empirical Application to Estimating the Preferences of LegislatorsThe RAND Journal of Economics, 1997
- The approximation of one matrix by another of lower rankPsychometrika, 1936