Going live!
Each week we rank Strictly contestants based on social media analysis. We call this the Strictly Sentiment score.
Week 7 and JJ goes. Of all the contestants JJ is the one who has caused us most problems. He doesn't have much of a Twitter following and our Sentiment score tends to underplay the amount of public support he has. Not this week though as we predicted that he would be in the dance off.
This week we successfully predicted that JJ and Jamie would be in the dance off. We have now predicted 10 out of 12 dance off places correctly based on Twitter sentiment. We are pretty pleased with this.
Next Saturday we are going to do something a bit different. We are going to analyse thousands of tweets about each dancer in real time. We usually wait until after the show to grab the tweets and do the analysis. But here at SPARK we really love a challenge and text analysis doesn't get more challenging than doing it live.
For Saturday's semi-final each couple dances twice. We will tweet their sentiment score after each round.
This really will be squeaky bum time for us.
Strictly Sentiment leaderboard
Last week we noted that Bill was losing his lead at the top of the Strictly Sentiment Leaderboard. Matters got worse for him this week as he tumbled to 4th place with Ranvir going top.
Onto the combined scores and this week HRVY gets the most combined points with Ranvir second and Maisie third. Jamie and JJ are firmly anchored at the bottom.
We will do it all again next week.
Don't forget that we tweet our prediction one hour before the results show on Sunday.
| Contestant | Judges | Strictly Sentiment | Combined score |
|---|---|---|---|
| HRVY | 6 | 5 | 11 |
| Ranvir | 4 | 6 | 10 |
| Maisie | 5 | 4 | 9 |
| Bill | 3 | 3 | 6 |
| Jamie | 3 | 1 | 4 |
| JJ | 2 | 2 | 4 |
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 10pm 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.
