Twitter Cannot Forecast Election Results

February 17, 2016 by Douglas A. McIntyre

White House
Source: Thinkstock
One of Twitter Inc.’s (NASDAQ: TWTR) benefits, according to advocates of the value to the public of the social network, is that it gives insight to social issues and news before the trends are obvious to the public and professional pollsters. With 300 million members, some of whom post their reactions to political issues, debates and elections, the argument might have some merit. It does not, according to new research.

After debates among Republican and Democratic candidates, the media uses Twitter as one measure of the momentum politicians have. The value of the measure stops at the ballot box, says a new paper published in the Social Science Computer Review. Among the conclusions:

Various studies have proposed the possibility of inferring public opinion based on digital trace data collected on Twitter and even the possibility to predict election results based on aggregates of mentions of political actors. Yet, a systematic attempt at a validation of Twitter as an indicator for political support is lacking.


In all tested metrics, indicators based on Twitter mentions of political parties differed strongly from parties’ results in elections or opinion polls. This leads us to question the power of Twitter to infer levels of political support of political actors. Instead, Twitter appears to promise insights into temporal dynamics of public attention toward politics.

So much for replacing or enhancing decades-old polling systems and practices. And so much for arguments that Twitter has use in the public forum beyond random tracking of events.