For over six and a half-decade the Eurovision Song Contest has entrained audiences from all around the world, not only from Europe!
In the next week, there will be the 65th edition in Rotterdam. May 18 and 10 (21:00 CEST) will be the semi-final and May 22 (21:00 CEST) will be the final. If you are curious about it, you can watch videos about competitors and the live on the official YouTube Channel!
Every year singers representing (almost all) European countries, Israel, and Australia compete for the best song. If the show is amazing, what is also entraining is the voting system. Each country can give a maximum of 12 points to the best song, excluding their own singer! Having good diplomatic relations is useful for succeeding in this competition! In addition to this, the audience can vote for the best song, but not one of their countries. But if you are, for example, an English worker in France, you can eventually vote the English song! Hence, the communities of immigrants are also crucial!
But here I do not want to go in deep about this aspect. I would like to give you an example of how you "play" with Eurovision Song Contest data.
Preparing some lectures about Python, I have recently read a nice post about the sentiment analysis for Eurovision Song Contest songs by AlanFrancisWise.
You can use an amazing “Eurovision Song Lyrics” dataset from Kaggle. This dataset includes the placings and lyrics from all the songs in the Eurovision Song Contest between inception in 1956 until the current edition of 2021 (of course we do not know the placing for 2021). The songs that were selected for the 2020 edition are also included. The sentiment analysis method and code are from Cristobael Veas’ analysis of Metallica lyrics. In his blog, he analyses Metallica lyrics over each decade.
If you want to play with this dataset for sentiment analysis, you can have a look at my Python code and dataset on my GitHub page .
What are the most used words in the lyrics of the 2021 editions?
Translating the lyrics in English, in the previous editions, love had supremacy. But this 2021 edition is different! Maybe the COVID-19, the lockdowns, but this year the most used words are:
know, feel, get, heart, and like!
If you are curious to see the most used word in the first three positions (in editions from 1956 to 2019), love has the supremacy for the first and the second position, but make for the third one.
Let's see if the 2021 winner will sing about love or the most used words of this edition!
Σχόλια