Blogs

Watson serves real-time analytic insight at Wimbledon

CTO Watson, Europe, IBM

Each year at Wimbledon we like to explore new types of technology innovation. This year, IBM’s Watson cognitive technology has been a major part of that innovation and I’d like to give you a peek at what we’ve been up to.

Watson "cognitive" technology refers to that which is in some way more human-like and interacts on our terms, rather than those of a computer. Frequently this means natural language processing (NLP) – so a computer can understand language written by a human, or perhaps enter into a conversation with that human to answer questions or clarify what they are looking for.

Last year, we used Watson technologies at Wimbledon to analyze tweets about the championships. To do this, we ingested massive volumes of Twitter data in real-time and then applied Watson’s natural language understanding to determine the topics and sentiment (positive or negative comment) of those topics. In this way we were able to see what the global audience was saying about the championships in real-time – a critical part of a social media strategy for a fast-moving event like Wimbledon.

This year we are extending the use of Watson by training a Watson system all about the championships themselves, such that members of the Wimbledon team can use it to ask questions and seek information about the event. We call this the “Wimbledon Digital Assistant” because it assists by finding relevant knowledge to solve a user’s problem. Today that is reserved for members of the events team, but we anticipate providing it to others in the future as Watson learns more about tennis.

Watson is famous for its leading-edge natural language processing – when it beat the world’s best Jeopardy! players we entered a new phase of sophistication in the way that a computer can understand the English language. The game show brought its own language challenges – it's famous for its unique style of questioning that makes it challenging even for us humans to grasp. Just like Jeopardy!, Wimbledon has its own particular form of the English language, with all of the tennis acronyms, and ensuring that Watson understands this has been one of our tasks this year.

When we first started analyzing the requirements for a Watson Wimbledon system, it quickly became clear that we have two related but distinct sources of information that Watson needed to understand. On the one hand, we have some rich sources of what might be considered 'general knowledge' about the championships – "why do the players wear white?" might be an example question. On the other hand, Watson also needs to know and to manipulate a lot of complex statistical data in order to answer questions like "what is Andy Murray's average serve speed?".

Next week we will look at how we approached this problem and how it has also been implemented across many areas of general business. In the meantime, perhaps you could look at creating something similar for your own business? Register today, or have a developer friend register, on IBM’s Bluemix and create your own "Powered by Watson" app using the cognitive services in the Watson Developer Zone.