Which Nordic country has the gloomiest Christmas songs?

16.12.2020 09:25 CEST/EET (UTC +2)

We turned to artificial intelligence in our efforts to determine the most cheerful and gloomiest Christmas songs in the Nordic countries. Norwegian songs were clearly the gloomiest, while the most cheerful songs came from Finland.

Artificial intelligence is often linked to complex problems that are difficult, or impossible, for humans to solve. For example, when studying the effects of medicinal drugs in the body, artificial intelligence can be used to explore how the three-dimensional structure of complex molecules comes into being. In this case, modelling helps replace years of experimental work in the laboratory. However, artificial intelligence can also be applied to solve much more common and simple problems. Tapio Linkosalo, Analyst at Innofactor, used sentiment analysis to determine the gloomiest and most cheerful Christmas songs in the Nordic countries.

“Despite the grandiose name, artificial intelligence and its applications mostly boil down to plain and simple statistical modelling. AI applications are highly automated and therefore well suited to the processing of large sets of data. They are also capable of identifying subtle interdependencies in data, which easily go undetected by humans. The analysis of the gloomiest Christmas songs is based on a sentiment analysis of text, which is really elementary for an AI application. In other words, the starting point for our problem-solving efforts was good,” says Linkosalo.

The model is based on the idea of determining the sentiment (either positive or negative) for each word in a song. The overall sentiment of the song then equals the average of the sentiments of individual words. The words used for the calculation were classified based on IMDd movie reviews and a number of tweets that had already been evaluated as positive or negative.

“Sometimes, the evaluation of an individual word may be unexpected. For example, a fan of gothic horror may describe a movie as being ‘wonderfully grim’, which results in the word ‘grim’ getting a positive evaluation. However, since I used thousands of reviews, each individual word got a number of different results, so I expect that the average of these results closely corresponds to the typical sentiment of the words,” Linkosalo explains.