About
The Premier League, celebrated as the most competitive and compelling football league in the world, oversees England’s top clubs and has a loyal global fan base.
Challenge
The Premier League aimed to validate its status as the most competitive and compelling sports league by analysing global fan sentiment using advanced data and AI insights.
Firemind used Amazon Bedrock’s LLM’s on AWS to analyse global fan sentiment from 977,337 social media posts on X (formerly Twitter).
Services used
- Amazon Bedrock
- AWS Lambda
- Amazon DynamoDB
- Amazon S3
- Global Validation: Confirmed Premier League’s global appeal.
- Out of the box thinking: Produced new thought lines for league analysis
Results
Global validation of the Premier League’s status as the world’s most competitive league
100% SOX compliance in Settlement process automation
A scalable platform built to analyse up to 1 million posts per month for continuous insights
>95% success rate of bot case completion
SDK delivered for native platforms, enabling Virtual & Live agent communications across multiple mobile platforms
As founder clients of Firemind, the Premier League has developed a strong and trusting working relationship over many years. As the company has grown, a personal and responsive approach has been maintained which underpins the support of our projects. The Premier League markets itself as the most Competitive and Compelling League in the world. This is hard to quantify with objective data, very often the consequences of being a successful league are quoted, Broadcast revenue, player demographics, audience reach as a sample. Firemind approached us offering an opportunity to work with Generative AI to parse large quantities of unstructured data for meaningful insight. The hypothesis was that the draw of the Premier League is at an emotional, psychological level and X Posts relating to the Premier League and other Leagues could be assessed. The Firemind team skilled in prompt engineering has interrogated the AI engine and refined the parameters to guide the output in the required directions. The project continues to develop with 1M Posts a month and will be further developed to assess other Social Media mediums including video and imagery.
