Kremlin analysts could have used Twitter as a source of military intelligence to inform their actions in the 2014 Russia–Ukraine conflict, a study has found.
University of California experts showed that location-tagged tweets by Ukraine residents could have been used to map out sentiments towards Russia in real-time.
The map they made of pro-Kremlin regions turned out to bear a striking resemblance to the actual areas to which Russia dispatched its special forces.
Specifically, this included Crimea and regions in the far east of Ukraine — where the incoming forces would have been most likely to be seen as liberators.
In contrast, the data could also reveal those areas where dispatching forces would have lead to greater resistance and corresponding casualties and costs.
The team stress that they are not presenting evidence that the Kremlin used Twitter to guide their Ukraine strategy, but only that the approach would have been viable.
Yet, the results reveal how not only how social media can polarised ‘opinion bubbles’, but moreover how these can be exploited for crisis decision-making.
Scroll down for video
Kremlin analysts could have used Twitter as a source of military intelligence to inform their actions in the 2014 Russia–Ukraine conflict, a study has found. Pictured, pro-Russia protesters come face-to-face with riot police in front of a governmental building in Kharkiv in 2014
The Russian-Ukraine conflict began in the wake of a revolution that saw the overthrow of the Ukrainian government and the ousting of the elected president, Viktor Yanukovych, who fled to Russia on February 21, 2013.
Protesters — who went on to assume power in Ukraine — had objected to the suspension of a planned association with the European Union in favour of greater ties to Russia and the Eurasian Economic Union.
Russia responded by treating the revolt as an illegal coup and refusing to acknowledge the interim government established by protesters.
As various anti- and pro-government militias emerged and clashed with each other, Russian special forces entered Crimea and the Donetsk and Luhansk states, or ‘oblasts’, beginning around February 27, 2014.
These special forces, however — despite being backed up by regular troops near the end of 2015 — did not push further north and west into Ukraine.
‘If you’re a conservative Russian military planner, you only send special forces to places where you are fairly certain they will be perceived as liberators, not occupiers,’ said paper author and political scientist Jesse Driscoll of UC San Diego.
‘A violent occupation of Russian-speaking communities that didn’t want the Russian soldiers to be there would have been a public relations disaster for Putin.’
‘So estimating occupation costs prospectively would have been a priority.’
University of California experts showed that location-tagged tweets by Ukraine residents could have been used to map out sentiments towards Russia in real-time. Pictured, Russian armoured personnel carriers and a truck seen on a road near the town of Bakhchisarai in 2014
A map the researchers made of pro-Kremlin regions based on tweets turned out to bear a striking resemblance to the actual areas to which Russia dispatched its special forces. Pictured, a Russian flag flies in the foreground as soldiers block a Ukrainian military base south of Simferopol, Crimea, on March 2, 2014
In their study, Professor Driscoll and fellow political scientist Zachary Steinert-Threlkeld of UC California set about to see if the pro-Russian areas of Ukraine could be determined based on the sentiments expressed on Twitter.
To identify the tweets that were relevant to the Russia–Ukraine crisis, the researchers began by creating vocabularies of key words and phrases that were commonly associated with the opposing narratives around the conflict.
‘All of this started with an event that the Kremlin still calls a “coup” and Western governments call “The Revolution of Dignity” — very different narratives there,’ Professor Driscoll explained.
‘The framing language of “terrorism”, was prominent in anti-Kremlin users and “fascism” was popular among pro-Kremlin tweets,’ he added.
‘These two narratives were frequently employed in news coverage during the six months in the study, including on Russian and Western television news programs.’
The social media-sourced data could also reveal those areas where dispatching forces would have lead to greater resistance and corresponding casualties and costs. Pictured, protesters clash outside of the Crimean parliament building in Simferopol on Feb 26, 2014
‘If you’re a conservative Russian military planner, you only send special forces to places where you are fairly certain they will be perceived as liberators, not occupiers,’ said paper author and political scientist Jesse Driscoll of UC San Diego
The team then applied these vocabularies to a database of location-tagged tweets posted from within the Ukraine over 188 days from February–August 2014, excluding tweets produced by automated accounts, or ‘bots’.
Focus was given to Russian-language posts, on the assumption that the Russian-speaking population of Ukraine would be the most likely group to be open to Kremlin messaging and protesting against the local authorities.
To begin with, the team identified a sample of 5,328 tweets from 1,339 accounts relating to the conflict, which were analysed by a team of Russian speakers in Ukraine and sorted into their political affiliation.
As various anti- and pro-government militias emerged, Russian special forces entered Crimea and the Donetsk and Luhansk oblasts beginning around February 27, 2014
From this, the researchers were able to map the distribution of these anti- and pro-Kremlin sentiments across each of Ukraine’s individual oblasts.
Although there were expressions on Twitter of pro-Kremlin sentiments coming from every oblast, the researchers found that Crimea was an outlier, one in which there was a high percentage of pro-Russian sentiment.
This was the region in which the Russian news narrative — that a fascist coup had taken place in Ukraine — really took hold in the local Russian-speaking communities.
Outside of Crimea and the far-East of the country, this framing resonated far less, potentially explaining why the Kremlin did not press further into Ukraine where they may have faced stronger and violent resistance.
Although there were expressions on Twitter of pro-Kremlin sentiments coming from every oblast, the researchers found that Crimea was an outlier, one in which there was a high percentage of pro-Russian sentiment
‘Our conjecture is that [Kremlin] planners would have been eager for information on social attitudes of Ukrainians,’ said Professor Driscoll.
‘If Russian strategists were considering expansion beyond Crimea, they would have been able to use social media information to assess, with a great deal of precision and in real time, the reception that they would likely receive,’ the researchers wrote.
‘Our data shows that further expansion beyond Crimea could have resulted in an ethnic bloodbath.’
A second analysis — using a larger dataset of tweets compiled by a machine learning algorithm trained on the first sample — identified 58,698 pro-Kremlin and 107,041 anti-Kremlin posts in total.
In this dataset, Crimea no longer stood out as an extreme outlier — instead, the maps emphasised the longitudinal dimension of the data, with more pro-Kremlin sentiments appearing in the eastern oblasts and anti-Russian tweets in the west.
In a second, larger dataset, Crimea no longer stood out as an extreme outlier — instead, the maps emphasised the longitudinal dimension of the data, with more pro-Kremlin sentiments appearing in the eastern oblasts and anti-Russian tweets in the west
In a second, larger dataset, Crimea no longer stood out as an extreme outlier — instead, the maps emphasised the longitudinal dimension of the data, with more pro-Kremlin sentiments appearing in the eastern oblasts and anti-Russian tweets in the west
‘Our claim is not that social media is the only way to get this information,’ Driscoll said, noting that the Kremlin has ‘lots of eyes on the ground’ in the Ukraine.
Yet at the same time, he added, Twitter ‘does provide a granular picture that analysts from different countries can observe in real time, even from a great distance.’
Similar techniques could be used to assess the sentiments of other demographics, the team note — with myriad military crisis-bargaining applications.
For example, such might allow Chinese analysts to require real-time updates on public opinion in Taiwan — or for the US to monitor popular sentiments among Iranian youths.
‘Our claim is not that social media is the only way to get this information,’ Driscoll said, noting that the Kremlin has ‘lots of eyes on the ground’ in the Ukraine. Yet at the same time, he added, Twitter ‘does provide a granular picture that analysts from different countries can observe in real time, even from a great distance’
‘We favour the analogy between information warfare techniques and airplanes at the start of the First World War,’ the researchers concluded.
‘Conventional militaries are just beginning to explore the ways that emergent information technologies can shape battlefields.’
‘As techniques for real-time data mining become commodified, they will be integrated into best practices for counterinsurgency and, more generally, into military planning.’
The full findings of the study were published in the journal Post-Soviet Affairs.
Russia and Ukraine: Key moments in their relationship
Ties between Russia and Ukraine have been turbulent since the fall of the Soviet Union, but deteriorated sharply after Kiev’s 2014 pro-EU revolution.
Amid a new peak in tensions over a naval standoff in the Sea of Azov, here is a recap of key moments in their relationship.
Limited Soviet independence
In December 1991 Ukraine votes in favour of independence from the Soviet Union in a referendum.
Russian president Boris Yeltsin accepts the vote and Russia, Ukraine and Belarus set up a Commonwealth of Independent States (CIS).
But over the next five years, Ukraine seeks ways to escape Russia’s guardianship.
Perceiving the CIS as an attempt to bring it back under Moscow’s control, it turns towards the West and seeks ties with the US-led NATO military alliance – a no-go for Russia.
Friendship treaty
In May 1997 Russia and Ukraine sign a friendship treaty that reconciles them but without removing a main source of tension: Kiev’s ties with NATO.
It settles a key disagreement by allowing Russia to retain ownership of the majority of ships in the Black Sea fleet based in Ukraine’s Crimea while requiring that Moscow pay Kiev rent to use the port of Sevastopol.
Moscow however remains Kiev’s most important commercial partner, with Ukraine totally dependent on Russian oil and gas.
Pro-West Kiev
Ukraine’s 2004 presidential election is marred by fraud and the victory of the pro-Russian Viktor Yanukovych provokes unprecedented protests in the peaceful Orange Revolution.
Ukraine’s 2004 presidential election was marred by fraud and the victory of the pro-Russian Viktor Yanukovych (pictured) provoked unprecedented protests in the peaceful Orange Revolution
It leads the vote to be cancelled and in December pro-Western opposition leader Viktor Yushchenko is made president.
In January 2005 Yushchenko makes his first trip to Russia in a bid for reconciliation.
The ‘gas wars’
In January 2006 Russian gas monopoly Gazprom suspends vital shipments to Ukraine after months of disputes over the price. The cut affects onward deliveries to European countries hit by a cold snap.
Russia again in January 2009 halts gas deliveries to Ukraine owing to the non-payment of debts, also suspending for two weeks all shipments to Europe via Ukraine.
There is another halt of several months in 2014 over outstanding payments from Ukraine, which is resolved after marathon EU-brokered talks.
Pro-European uprising
In November 2013 Yanukovych, president since 2010, suspends talks on a trade and political pact with the European Union in favour of closer ties with Russia.
It sparks weeks of massive protests by pro-European opposition groups demanding the pro-Russian ruler quits.
The uprising, centred on Kiev’s Independence (Maidan) Square, comes to a head in February 2014 when police fire on protesters.
Nearly 90 people are killed, bringing the toll from the three-month uprising to around 100.
Yanukovych flees to Russia and an interim government is installed.
Russia annexes Crimea
Pro-Russian demonstrators clash in February 2014 with supporters of the new interim authorities in Simferopol, the capital of the Crimea peninsula.
Russian gunmen seize parliament and government buildings, and raise the Russian flag.
Pro-Russian soldiers in unmarked uniforms arrange a position on top an APC near Ukrainian marines base in the city of Feodosia, Crimea, on March 23, 2014
On March 16 pro-Moscow officials in Crimea hold a referendum on seceding from Ukraine and joining Russia.
An overwhelming 97 percent of Crimeans vote in favour, although the move is deemed illegal by Kiev and Western capitals.
Two days later Russian President Vladimir Putin signs a treaty absorbing Crimea into Russia.
Separatist rebellion
In April 2014 a pro-Russian rebellion erupts in Ukraine’s industrial eastern areas with demonstrators seizing local government buildings.
Pro-Russian officials in Donetsk and Lugansk declare their regions to be independent.
Ukraine and its Western allies accuse Russia of instigating the uprising and pouring in arms and troops to bolster the self-proclaimed republics. The Kremlin denies the claims. The conflict has since then left more than 10,000 people dead.
By AFP
