Fun Bill Three - it ain't what you do it's the way that you do it

Each week we rank Strictly contestants based on social media analysis. We call this the Strictly Sentiment score.

Week one of Strictly and the first of the marked dances. No eliminations this week and so no public vote. That didn't stop us doing a sentiment analysis of tweets about each contestant and ranking them based on our Strictly Sentiment score.

Although ranked 8th of the 12 couples by the Judges, Bill and his dancing partner Oti, wowed the audience on Twitter to be ranked first on Strictly Sentiment. But as with the judges, it wasn't Bill's twinkle toes that got people excited. Instead, it was the fun and laughter that he brought to the routine. He seemed to be having the time of his life and this is was stuck in people's minds.

Nicola came second on Strictly Sentiment and equal third with the judges. There was a lot of positive sentiment for her technical ability and a lot of love for her partner Katya. The thing that stood out for people was her smile and the obvious fun she was having. For this week at least, having fun played a big part in our Strictly Sentiment scores. 

Third place on Strictly Sentiment is HRVY. The judges considered him to be the best dancer on the night. Twitter considered his jive to be amazing and full of energy. What he lacks in vowels he makes up for in swivelling hips!

At the other end of the leaderboard, Jacqui, Max and Jamie recorded the lowest Strictly Sentiment score. Jamie finished last on Strictly Sentiment with tweets about his lack of technique and stiffness being more prevalent than those about the energy he brings. There is a view that he will improve with time. But will he be given the chance?



Strictly Sentiment leaderboard

No elimination this week but we've combined the judges scores with the Strictly Sentiment score to show what might have happened. As with the show itself we have assigned scores based on where each contestant ranks.

Strictly Sentiment score

The Strictly Sentiment score is derived from a sentiment analysis of tweets. Using natural language programming and machine learning we classify each tweet as positive, neutral or negative. Tweets are filtered so that they only relate to a celebrity's appearance on the show rather than what they do in their 'day job'. Only tweets made between 7pm and midnight are included. This is to ensure that tweets relate to Strictly.

We then add up all the positive tweets for each contestant and assign a score between 1 and 100.  This score is based on the relative distribution of positive tweets. We do this to make it easier to compare and contrast Strictly Sentiment scores.