Using German data, including more than 10 million tweets, a new study published in the American Journal of Political Science demonstrates that the state of public discourse about immigration and support for radical right parties is influenced by perceived threats from ethnic and religious minorities.
Despite the fact that Twitter users’ location information is often inaccurate, the authors were still able to geolocate 189,368 users in 235 of Germany’s 261 constituencies. They found 5,512 Twitter accounts that only shared information about local landmarks and assumed that anyone who followed three or more of these accounts must be a resident of the area.
A daily measure of how closely the language used by parties on Twitter matched that of the public in a specific constituency was calculated using a natural language processing algorithm. Twitter users in any given constituency were assumed to be politically aligned with national parties based on this similarity metric.
According to researchers: “We study the role of perceived threats from other cultures induced by terrorist attacks and criminal events on public discourse and support for radical-right parties. We develop a rule which allocates Twitter users to electoral districts in Germany and use a machine-learning method to compute measures of textual similarity between the tweets they produce and tweets by accounts of the main German parties.”
“Using the exogenous timing of attacks, we find that, after an event, Twitter language becomes on average more similar to that of the main radical-right party, AfD. The result is driven by a larger share of tweets discussing immigrants and Muslims, common AfD topics, and by a more negative sentiment of these tweets. Shifts in language similarity are correlated with changes in vote shares between federal elections.”
“These results point to the role of perceived threats from minorities on the success of nationalist parties.”
