Abstract
Can the engagement parties receive on social media tell us how they will do at the polls? Studies of Twitter have reached mixed and often optimistic conclusions, but parties' own Facebook pages, where supporters respond to what parties post, have rarely been tested across many elections. I compare the share of Facebook interactions each party's page received in the four weeks before national elections with its share of the vote, for 207 party-elections in 34 elections in 15 European countries between 2010 and 2020, using posts collected through CrowdTangle. Among the 181 party-elections with a previous result, engagement shares were related to vote shares (correlation 0.60), but much less closely than the previous election result was (0.94). Once the previous result is known, the campaign engagement share added little, and what it added was not distinguishable from audience size before the campaign. Changes in engagement share during the campaign showed no clear relation to changes in vote share. Among parties whose vote share changed by at least a point, the direction of the change in engagement share matched the direction of the change in vote share in 52% of cases (62 of 120). In forecasts made one election at a time, adding engagement did not reduce the average error of just under four points from the previous result alone, and engagement alone more than doubled it. The party with the most engagement won the most votes in only 12 of 34 elections. On Facebook, likes appeared to measure the size of parties' audiences more than the movement of the electorate.
Cite
Hotham, T. (2026). Do Likes Predict Votes? Facebook Engagement and Election Results in Europe, 2010 to 2020. Preprint, Zenodo. https://doi.org/10.5281/zenodo.23414618