AI and Russian propaganda: it’s not what it looks like

[Note: This article was originally published in the On Think Tanks Annual Review. It was written by David Sichinava and Dustin Gilbreath. David Sichinava is the Research Director of CRRC Georgia. Dustin Gilbreath is the Deputy Research Director of CRRC Georgia and the Communications Manager at Transparify. The views presented in this article do not reflect the views of East West Management Institute, USAID, or any related entity.]

In the think tank world, talk about artificial intelligence (AI) is common. Using it is less common. One of the underlying causes of this may be a perceived lack of familiarity with the methods. However, AI methods – including machine learning – are probably more familiar to many thinktankers than they realise. The Russian Propaganda Barometer project, recently conducted by the Caucasus Research Resource Centers (CRRC) Georgia, demonstrates the potential of these tools in think tanks for policy insight – particularly relating to discourse analysis, and developing targeting strategies.

Artificial intelligence and machine learning are more familiar than thinktankers think
To say that artificial intelligence in general, and machine learning algorithms specifically, is a dramatically changing industry would be an understatement. From optimising electricity usage in factories to deciding which advertisement to show you online, algorithms are in use all around us. In fact, algorithms have been shaping the world around us for decades.

The think tank and social science worlds are no exceptions to this. Indeed, most policy researchers will be familiar with, if not users of, algorithms like regression. Notably, this is a common tool in the machine learning world as well social science research.

Hopefully, knowing that regression is part of the machine learning toolbox will make it clear that machine learning is less foreign than many thinktankers may think.

While regression is one method in the machine learning toolbox, there are others. Although these methods are not new, this larger toolbox has only become commonly used in recent years as big data sets have become more available.

For many products and problems, machine learning solutions might be improvements on existing think tank practices. This is particularly true when it comes to developing a targeting strategy for programming, monitoring, or anything that focuses on understanding discourses.

The Russian Propaganda Barometer Project
CRRC Georgia implemented the Russian Propaganda Barometer project, funded by USAID through the East West Management Institute in 2018-2019. The project aimed to understand and monitor sources of Russian propaganda in Georgia, and to identify who was more or less likely to be vulnerable to the propaganda.

To monitor Russian propaganda, CRRC took all of the posts from public Facebook pages of potential sources of Russian propaganda (around 50,000 in total) in the Georgian language as identified by two other organizations working on the issue in addition to several pages missing from their lists. These posts were then analysed using natural language processing tools such as sentiment analysis. Network analysis was also conducted to understand the interlinkages between different sources.

One of the key insights from the project is that most of the sources of propaganda identified were in fact from far right organisations. While some of these are likely tied to Russia, an analysis of how they talked about the West and Russia suggests that most actually have more negative attitudes towards Russia than the West.

The analysis also called attention to the sharp rise in interest in the far right in Georgia. The number of interactions with far-right pages had increased by roughly 800% since 2015. While overall increasing internet use in the country likely contributed to this, it seems unlikely to be the only cause of the rise.

The results were presented in this dashboard, as well as a more traditional report. It enables users to see what the far right is talking about on a daily basis, and networks between different groups, among other metrics.

The project also aimed to inform a targeting strategy on countering anti-Western propaganda. To do so, we merged data from approximately 30 waves of CRRC and National Democratic Institute surveys that asked about a variety of preferences. From there, a ‘k-nearest neighbours’ algorithm was used to identify which groups had uncertain or inchoate foreign policy preferences. This algorithm basically identifies how similar people are based on whatever variables are included in the algorithm. Based on similarity, a prediction is then made about whatever outcome is of interest. This led to an algorithm that provided accurate predictions about two thirds of the time as to whether someone would be more or less likely to be influenced by Russian propaganda. Further research showed that the algorithm was stable in predicting whether someone was at risk of being influenced, using data that did not exist at the time of the algorithm’s creation.

The data analysis, while cutting edge in many respects, is not beyond the means of many quantitative researchers. Neither of us have MAs or PhDs in statistics: David is a geographer and Dustin is a political scientist.

While the Russian Propaganda Barometer addressed the research goals, we’d like to highlight that AI is no panacea. For the project’s success, we combined traditional think tank analysis of the situation in Georgia with AI to generate new insights.

The Russian Propaganda Barometer project is just one type of application of machine learning to policy research. There is good reason to believe more and more policy researchers will use these methods given their ubiquity in the modern world, together with the increasing availability of the large datasets needed to study these issues.  We hope that the Russian Propaganda Barometer project can serve as food for thought for others in service of this goal.

Georgia’s far-right are anti-Russian but share Russian narratives

[Note: This article was published in OC-Media. It is available in Georgian, here. David Sichinava is the Research Director at CRRC-Georgia. The views expressed in this article represent the views of the author alone. The article was written within the auspices of the Russian Propaganda Barometer Project funded through the East-West Management Institute’s ACCESS program.]

A USAID-funded study by CRRC-Georgia released on Monday shows that the far-right in Georgia is engaged in activities similar to their Russian supported counterparts in the European Union but speak more negatively about Russia than the West. Whether witting or unwitting, the implications are far-reaching for Georgia.

Since the mid-2000s, numerous media and academic sources have alleged that Russia is weaponising far-right and anti-liberal politics worldwide. This can be seen in Russian support for organised far-right groups within the EU, which in turn are used to attempt to influence domestic and regional politics.

Russian political elites have further used the anti-liberal far-right through the promotion of what has been called the ‘Russian model’ of authoritarian rule.

A crucial component of the model promotes Russia’s image as a protector of ‘traditional values’, including pro-religious and socially conservative views. Taken collectively, these far-right groups’ efforts can be understood as aimed at manipulating European public opinion through engendering anti-liberal sentiment within the EU.

To understand potential sources of Russian propaganda in Georgia and the far-right more broadly, CRRC-Georgia’s study analysed more than 26,000 posts from approximately 70 far-right Georgian-language Facebook pages.

The data suggest a growing appetite among Georgians for radical right-wing ideas. Between late 2015 to mid-2018, page likes for far-right pages increased eight-fold, from 89,000 to 760,000. Although there is clearly increased engagement on social media, this likely also reflects increased internet penetration in Georgia, with new internet users with previously far-right ideas finding far-right Facebook groups.


Besides purely nationalist sentiments, these groups are apt to criticise the liberal world order from a right-wing perspective, thus resonating with what Russia has endorsed. Some pages also reflect specific Russian talking points.

An illustrative example of right-wing, Georgian-language Facebook pages amplifying pro-Russian narratives can be seen in online opinions toward the US-funded Richard Lugar Centre for Public Health Research in Tbilisi. Since its opening in 2013, Russian politicians have been especially anxious about the establishment of the centre and frequently claim it is a test site for biological weapons. Following the loss of 15 lives to a flu outbreak in Georgia in early 2019, several right-wing pages shared posts accusing the laboratory of causing the outbreak.

While the number of social media posts talking about the lab in relation to the flu outbreak was small (18), their messages reached a wide audience: these 18 posts earned 754 likes from visitors and were commented on 538 times. Social media posts in which right-wing groups discussed the Lugar Laboratory were shared 1,639 times.

As previous analysis has highlighted, Georgia’s far-right is a heterogeneous crowd, and labelling them uniformly pro-Russian is misleading. In fact, the analysis of 26,000 social media posts shows that Georgia’s far-right speaks more negatively about Russia than the West on the whole. A sentiment analysis, a machine learning technique, scored conversations about Russia as net negative compared with almost neutral for the West.

Still, some pages which have pro-Russian slants also boast large followings. For instance, before being blocked by Facebook, Georgian Idea had about 40,000 subscribers. Another nationalist group, Georgian March, is followed by over 17,000 users and another 16,000 users subscribe to its content. On the whole, both groups speak more positively than negatively about Russia.

The analysis also suggests that pro-Russian pages actively engage with their audiences. Content created by the pro-Russian Georgian Idea garnered about 25,483 comments and 180,026 likes, while pro-Russian Georgian March attracted 32,761 comments from users. Importantly, other nationalist pages were less successful in engaging their audiences.

In contrast to the above pages, a large majority of far-right groups were not explicitly pro-Russian. Rather, the content of their messages was critical of both Russia and the West. The latter is usually criticised for pushing Georgia to accept a ‘liberal political agenda’. In contrast, Russia is portrayed as an enemy responsible for Georgia’s territorial conflicts.

While there is little besides circumstantial evidence that (parts of) Georgia’s far right is funded by Moscow, the data show that they do propagate messages that resonate with the Russian government’s vision of the world.

Despite sharing a similar vision, most far-right pages attack Russia with more vigour than the EU. While it is unclear whether some of these groups are backed by Russia, it is clear is that they at least amplify if not plant pro-Russian sentiments among the Georgian public.

Anti-western discourse dashboard: Tracking what the far-right is talking about on Georgian language Facebook

Within the framework of the Russian Propaganda Barometer project, funded by EWMI’s ACCESS program, CRRC-Georgia developed an anti-Western discourse dashboard. The dashboard visualizes what known sources of anti-western propaganda in the Georgian language have been talking about on Facebook since 2015.

The dashboard has a number of functions. It uses thematic modeling to identify what subjects people have been talking about over the years. The topics which different groups have been talking about are also provided by different sources of anti-Western propaganda. In addition, how the different groups (positively or negatively) talk about the West and Russia is provided on the dashboard’s landing page.


Besides the above, the dashboard has a wide variety of other tools. The posts page provides the number of posts on any given day as well as the number of likes, comments, frequency of sharing different sites the construction of networks between different sites, and activity levels during different parts of the week and time of day.


On the tool, the texts tab provides an analysis of the frequency of use of different words and bi-grams for different words used in connection to Russia and the West.


The tool is only available in Georgian, but over the course of the coming months, this blog will have posts describing findings from the data collected on anti-western discourse on Georgian language Facebook in English. To see a previous report from the same project click here, and an article based on that report, click here.