Sport is about people. So is data.

With the European championship hours away from the first match, you can feel the excitement. People are gathering to support their national teams, and everybody has a common topic to debate. For the following month, there will be a lot of talk around winning teams and football statistics. It really seems that football is all about people. But then again, so is data.

Using Watson Analytics for Social Media, I was inspired to look a bit closer at what people are talking about during this football competition: groups, teams and players. The first thing I noticed is that conversation is building up as the event is approaching.

Another insightful information is that the championship is not a hot topic only in Europe, but also in the USA. Although we should keep in mind that this analysis has been run in just four languages (English, French, German and Spanish), the amount of conversation in the US is still impressive.

The darker the color, the more conversation around the football tournament.

But I wanted to know more: which football group has the most conversation around it? It appears that group B has the most popularity, mostly since the England team drives a lot of engagement.  

Still, this is only scratching the surface. In theory, being talked about is a good thing, but are these mentions positive or negative? Recognizing positive and negative words and phrases, Watson Analytics determined that group A (the second as total number of mentions) has the most negative mentions, followed by groups B, E, C, F and D.

Coming back to the conversation amount around teams, we can see that as a national team, England has the greatest share of voice around it. Even when we took out the data originated in the UK, England is still the team the most talked about.

Despite this, the overall positive sentiment is more in favor of Russia, Spain, Portugal and Iceland. This is a mix of supporters encouraging their teams and context – for example, since this is Iceland’s first major tournament, there is a lot of positive content around the team and players.

Further on, people are already making predictions on which teams will be in the quarter-finals and the semi-finals. Again, England is the favorite, followed by France, Belgium, Germany and Spain.

There is also a lot of interest around players, not only around teams. Below, you can see the 20 most talked about players in the last 10 days, for this tournament. Cristiano Ronaldo, Zlatan Ibrahimović and Sergio Ramos are in top 3.

Again, as we pointed out before, not all mentions are positive. Another interesting statistic shows us what sources gather positive or negative comments for the players. For instance, we can see a negative sentiment graph by source (Twitter, news, videos, Facebook, forums or blogs) that tells us that Mats Hummels is associated with negative terms especially in articles and news, while Ibrahimović on Twitter and Ronaldo in videos.

Did you think about who the top scorer will be? It seems that Cristiano Ronaldo is the public’s favorite. Maybe we shouldn’t overlook Dimitri Payet either.

If football is a game about interaction, then this analysis is the perfect way to show it. Whether it’s the winning team, the top scorer or the most popular player, people have a clear idea on what they think will happen. There is no limit to what you can find out about what makes people tick in Social Media. Do you want to see which channel drives engagement, or what type of post has the greatest impact? It’s all here!

If you want to see more about what you can do with Watson Analytics, both personally and professionally, click here.

Get busy in the analytics game following #datagames on Twitter!