Russia’s invasion of Ukraine in 2022 significantly accelerated the shift from Russian language to Ukrainian on social media in what may signal a move towards greater Ukrainian self-identification, according to new research from the University of Bath, Ludwig-Maximilians-University Munich, and the Technical University of Munich.

Researchers examined nearly three million tweets from nearly 42,000 Ukrainian citizens from January 2020 to October 2022 and confirmed that the slow drift away from Russian observed since Ukrainian independence sped up dramatically following the invasion in February 2022.

In 2020 there were over 2,000 tweets daily in Russian compared to around 1,000 in Ukrainian and around 400 in English. By March 2022, the numbers of tweets in Russian and Ukrainian were roughly equal at around 1,000 a day, with around 250 in English, but by November of that year, Ukrainian tweets had surged to nearly 2,500 a day while Russian and English language tweets were now around 500.

“The data also shows that, of the people predominantly tweeting in Russian before the war, roughly half of them are now tweeting more in Ukrainian. And it is striking that around a quarter of them have performed a ‘hard switch’ to tweeting predominantly in Ukrainian,” said Dr Brit Davidson of the University of Bath’s School of Management.

“The data indicates a major behavioural change, which we would suggest is a highly politicised response by users who want to affirm their Ukrainian identity. We also observed that the Russian speakers who performed a hard switch to Ukrainian seem to be more active on Twitter, potentially as a desire to publicly distance themselves from Russia,” she said.

The research team conducted an extensive spam filtering scheme, removing duplicate tweets and training a bot detection model to remove potential spam bots. They also removed users who posted more than 100 tweets per day.

Only tweets from Ukraine were counted and re-tweets were excluded, leaving only primary tweets, quotes and replies. That process removed around 1.4 million Tweets and 21,000 users to create the cleaned-up data set of nearly three million Tweets and 42,000 users.

The researchers noted that, following Ukraine’s independence in 1991, many people in Ukraine considered themselves Russians by nationality or Ukrainians with Russian as their main native language. Census results showed that attempts to create a defined Ukrainian identity were only moderately successful.

However, the Euromaidan protests of 2013, where people demonstrated for closer alignment to the European Union, followed by the Russian military intervention in Crimea and the Donbas created a consistent and substantial shift away from Russian ethnic and linguistic identification.

“Interestingly, we had also seen a long-term behavioural shift away from English tweeting activity until late November 2021 but this reversed and even substantially increased as Russian troops mobilized along the Ukrainian border – we would suggest that Twitter users wanted to let the world know what was happening and issue a call for help in a language more readily understandable around the globe,” said co-researcher Daniel Racek from LMU’s Institute of Statistics in Munich.

As the war unfolded and the international community began to support Ukraine in various ways, that brief spike in English use faded to just above pre-invasion levels as users returned to their intra-national discussions in their native languages but much more in Ukrainian than before the invasion.