Eurovision 2019 Stats - NLP analytic tool reveals audience mood on social media reflects public vote
Updated: Jul 8
That’s it, the 2019 Eurovision Song Contest is over.
Congratulation to Duncan Laurence for winning the 2019 Eurovision trophy with his song Arcade. And good “morning after” to the Netherlands, keep enjoying the glee of victory
At Affogata.com (previously Communit360), the voting process was a nail-biting experience.
Reading Social Media Engagement
Unlike most viewers, Affogata team was not watching just to enjoy the show. The social reputation and social media engagement monitoring and analytics AI software was hard
at work analyzing the audience mood based on the content of their public interactions on social media designed. We had partnered with KannTV to follow the popularity of the Eurovision songs in real time on social media. KannTV, an Israeli digital TV channel
was broadcasting from their studio, providing ongoing commentary throughout the competition, relied on Affogata to gauge the mood of the audience and the popularity of
the songs, and our proprietary Natural Language Programming based AI solution raised to the challenge.
need a video
So, on the big night, as the points granted by the professional judges were being announced, the mood at Communit360 was one of growing doom. Our system had Norway as the winner, and it barely raked 57 points from the professional judges, trailing very low on the scoreboard.
When Norway received a whopping 291 points from the public vote, the relief at Affogata HQ was palpable. Public opinion was backing our findings. It was the judges who had opinions differing from that of the audience, and our algorithm was not built to second guess Eurovision judges, only to analyze the trends derived from social media activity.
Still, we had to wait until all the public votes were counted to get confirmation that our system was indeed extremely accurate in evaluating the audience’s mood from data collected on social media and analyzed by our AI.
First Eurovision 2019 Semi-Finals Results and Affogata Estimates
Second Eurovision 2019 Semi-Finals Results and Affogata Estimates
As Affogata had predicted, Norway would have won the Eurovision had the results been based exclusively on the audience’s vote.
This confirmed our team’s hard work in building the predictive algorithms, as, during the first and second semi-finals, Affogata had 80% correct prediction rate in identifying the contestants who would proceed to the finals.
Affogata is not at all designed
to be a predictive tool, but
rather to measure brand’s
reputation, identify terms that
are commonly used to refer to
the brand or compare different
brands, so we were elated by
this unexpected predictive success.
Spotting Unexpected Trends
Communit360 is more geared to identify unexpected trends. For example, in Norway’s case, amongst the predictable mentions of the song and the contest, we noticed numerous mentions of “bald guy”, both positive, neutral and negative
So, it seems that Fred Buljo’s baldness was a feature gathering considerable notice. Trying to understand what is behind the interest for the baldness of one of the band members, we quickly glanced at all the times it is referred to, either positively, negatively or neutrally.
Looking at these tweets, we immediately see that the “feature” bald guy is used as a way to identify a specific singer in Keiino, an easy way to refer to a specific singer in the band.
This kind of data is of high value for brands and trend discovery, as such insight about an unexpectedly salient feature could be leveraged for marketing purposes. For the band choreographer, stylist or other show managers this is valuable information about where the audience’s attention is directed. It would help them to design the set or the costume to maximize or minimize the impact of the baldness of the “bald guy” depending on the effect they want to achieve.
Accurate information is at the root of management, and accessing such fine-grained data in realtime is of immense value to adjust behavior, design, course of action, feature development, marketing campaigns and more.
There are many other features based on Affogata AI, such as comparing between countries or brands, getting data about the exact number of people commenting on any topic and their combined reach, the most engaged tweets and much more, however, for now, it is time to recover from the exciting night following the Eurovision contest.
Reveling in the Popularity of Affogata’s Live Analytics
NEED HERE VIDEO
Another highlight of the Eurovision for our team was the popularity of our live statistics on the Twittersphere. Sooo many chose Affogata public real-time analytic dashboard to share their excitement about the songs they supported! So, again, congratulations to the Netherlands for their victory, and heartfelt congratulations to Norway for their victory with the public vote! And to Affogata for its accuracy