The Final: We cracked it!
Winner: Harry Judd
Second: Chelsee Healey
Third: Jason Donovan
What the data told us for the final week:
It’s the final and we’re down to the final three celebrities. The data showed Harry Judd emerging as the front runner a few weeks ago and that’s still the case this week, though Chelsee Healey is hot on his heels.
The chart shows significant spikes for all three celebrities during the live shows, with Harry generating the most buzz for two of the past three weeks, and Chelsee creeping up to steal his thunder last week. The easiest conclusion to draw from the data is that Jason Donovan will be the first to exit the final, as buzz around his name is consistently and significantly lower than that for the other two celebrities.
As for the winner, we’re sticking with Harry as our pick. He’s a fabulous dancer, he’s gorgeous and he has constantly out-buzzed his competitors!
A look back at Strictly 2011
The first thing to say is that we found out very early on that predicting the loser each week is much harder than predicting the winner of the whole show!
The first issue we encountered was that of collecting clean data for the celebrities. Is there a more generic name out there than “Alex Jones”? Perhaps John Smith, but after that… It took us a few weeks of trial and error to be entirely happy that the data we were looking at was actually about the right people.
Another issue was in examining the sentiment behind the celebrities’ buzz. Our experience told us that volume itself was no sign of popularity, as people love to get on social networks to have a good whinge as much as they use it to declare themselves a fan – if not more! We developed a tool for sentiment analysis that does a pretty good job of sorting the positive from the negative, but there’s no tool out there that is 100% accurate.
One week, for example, someone tweeted “@bbcstrictly bloody hell that was absolutely fab…u…lous!! Len you are wrong #scd” – our tool put this firmly in the negative camp, but clearly it’s not!
All that was before anybody had even danced a dance. We found that the volatility in the dancing performance by the celebrities made it very difficult to judge what would happen. As the couple that leaves is decided by a combination of the judges’ score for their dance and the phone vote, a novice celebrity doing the paso doble one week and a waltz the next might be near the middle one week and then rock bottom of the judges’ score the next. We quickly had to factor this fluctuation into our algorithm, allocating a score for the perceived difficulty of the dance celebrities were undertaking each week.
So how did we do? We have a slightly lower than 50% success rate but would argue that using the data is slightly more effective than randomly guessing. As we pack away our crystal glitter ball for another year, this analysis has shown that data on its own isn’t enough. Without understanding the context and the content of the data we would have been way off the mark every week. By examining the source and taking into account the limitations of our data, we can be much more calculated in the way in which we read it.
See the full article Guardian article here.
Can Reform predict the winner of Strictly Come Dancing for a second year running?
Twelve months ago Reform’s analysts predicted that Kara Tointon would be the winner of Strictly Come Dancing before she and her dance partner Artem Chigvintsev had even set foot on the dance floor in the first week of the competition: http://www.reformdigital.com/blog/strictly-come-searching
How? By analysing search and social data, of course! (Ssssh! Don’t tell the Bookies!)
Digital data is the new barometer for national popular sentiment. Every second of every minute of every hour of the day, someone is registering an opinion online – about TV celebrities, pop stars, authors, football clubs, political parties – even white goods manufacturers.
Yet for business leaders, brand strategists and agents to the stars digital data offers valuable insight into how our brands and products are performing and what esteem they are held in. At an even deeper level it provides an intimate understanding of our brands that we, as their owners may not possess, and highlights risk that we had not planned for.
As digital consultants it is our job to gather this data, to analyse it and to provide our clients with relevant and actionable insights that can help their businesses – and brands – to grow.
Through our work with digital data we have saved brands from the brink of ruin, we have identified and nurtured new customers for our clients, and we have converted online engagement into sales revenues.
This year we’re delving into the Strictly data once more. The BBC have created a longer ‘build up’ to the start of the show this year, which means that people have been talking about it online for longer, so the data set is more robust in size.