Can Social Media Analysis Predict The Strictly Come Dancing 2022 Winner?

Sequins at the ready! Strictly season is upon us! The Twittersphere is already lighting up with conversation over this year’s celebrity pairings and who fans are throwing their support behind ??

Over the past two years, our team of data analysts and social listening experts enjoyed a 75% strike rate when it came to dance-off predictions, revealing couples who would feature in the dance-off on six of a possible eight eliminations.

The Mediaworks team is back and ready to rumba once more. Through the series we’ll be analysing a sample of 1,000 tweets about each celebrity to gauge public opinion on the latest intake.

Can the sentiment of the public’s social media posts accurately predict the outcome prior to the weekend’s voting?

What Is Social Sentiment Analysis?

Social sentiment analysis allows us to see if people are being discussed in a positive or negative way on social media. Mediaworks used AI technology to analyse the most recent 1,000 tweets relating to the 15 Strictly celebrities and their dance partners. We will assign a score for each contestant each week based on new tweets that are generated.

What Is The Sentiment Score Based On?

Sentiment score places a value on the emotion displayed in each tweet and attributes a score to the post, where individuals can score between -10 and 10, where -10 is extremely negative and 10, the maximum, is extremely positive.

Each contestant will be assigned a score every week based on new tweets that are generated.

Follow us through the next 13 weeks to see who is crowned the Strictly Come Dancing 2022 champion! We’ll be running weekly updates to predict who will leave each week, while also tracking the growing sentiment as celebs transform into Fred Astaire and Ginger Rogers.

The data presented by Mediaworks above is a sample and does not reflect the views and opinions of Mediaworks, nor is it representative of the entire population. The data presented is subject to third party machine learning algorithms, as well as human interpretation.