One more reason why Ukraine is NOT Russia

Russian imperialists claim that Ukraine has no right to exist on its own. It’s a historical part of the big Russia. As a result of some historical accidents, it became a separate country, which got estranged under the Western influence.

But how similar are Ukraine and Russia if we use distributional semantics? This is a very popular approach in computational linguistics. One takes a large collection of texts, processes them and gets automated measures of similarity between words or phrases. The basic idea is very simple: If two words occur in similar contexts, they will have higher similarity.

I’ve created a word2vec model based on almost 900 Putin’s speeches, starting from his inauguration in May 2012 to August 2022. Next, I asked the model how similar the words “Russia” and “Ukraine” are. The answer was 0.34. Is this a lot? Not really. There are many countries that are more similar, according to the model. For example, France and Germany have a similarity score of 0.81. Even North Korea and South Korea are more similar, with the score of 0.61.

In fact, “Ukraine” is much more similar to the West (0.77), NATO (0.73), the USA (0.72) and Europe (0.63), than to Russia. Russia, in its turn, is not very similar to anything. I bet Russian patriots will be happy to hear that. They have always been proud of its “special path”. Russia’s highest similarity score with another country is 0.44. Strangely enough, it is Germany, which is closely followed by Europe and India (both approximately 0.43), and Belarus and China (0.42).

To sum up, we see that Putin’s own speech contradicts his propaganda. Ukraine is not Russia. Even worse, it is part of the West. Russia is alone in its “splendid isolation”.

And now comes the most shocking discovery. Brace yourselves! The model says that the Crimea is more similar to Ukraine (0.55) than to Russia (0.44). The difference is even larger for Donbass: its similarity score with Ukraine is 0.58, whereas with Russia it’s only 0.22! After all the years of Russian propagandists’ hard work. Could it be that Putin’s subconscious (or that of his speechwriters, of course) sabotages his masterful plans? I wouldn’t mind that.