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.
Highlights
Scholars have used social media data to measure elite and mass ideology [1, 2], but few efforts have been made to compare measures from social media with polls and to forecast elections using social media data
By assuming that users are more likely to like the posts from fan pages that are closer to their own ideological position, we are able to place politicians, news outlets, interest groups, and ordinary citizens on the same ideological spectrum
By comparing Facebook support rates and polling averages with actual vote shares, we find that polling averages systematically overestimate Clinton’s support in right-leaning states, while Facebook support rates often overestimate those of Trump
Summary
For the parts of the replication that individual level data is needed (Figs 1 and 7–9, S6 and S7 Figs), the authors uploaded a random sample of individuals (1 or 10 percent, depending on the context, where the procedure is documented in the code in the replication file) with their user_ID hashed. This will protect individual’s privacy while ensuring the replicability of the result.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
