Innovation

AI helps the fan understand how top sportspeople achieve greatness

Share this post:

In the pursuit of greatness, it’s not enough to look through a single lens. IBM Watson tackles the challenge of seeking a deeper understanding than ever before, into what makes sporting excellence.

IBM has been supporting Wimbledon’s pursuit for greatness for a staggering 29 years. Each year the partnership reaches new heights, and this year is no different. Building on the foundation of analysis done in 2017 for #WhatMakesGreat, the team set out to explore the data in a new way; looking this time at how elite sports people find their advantage.

It was clear from the start that comparing excellence across different sports would not be trivial. With a huge pool of data at our finger tips, the team of statisticians, sports analysts, journalists and IBM Watson Developers set about exploring the open-ended question by leveraging both machine and human intelligence. By using IBM Watson, a cognitive platform, we were able to generate unique insight and explore the topic through its ability to understand natural language and analyse unstructured data.

We provided Watson with over 25 years of tennis and sports data from articles, blogs and interviews, 350,256 documents in total. We then used Watson Discovery service (WDS), one of several services available, to explore and extract meaning from the unstructured data. We also used Watson Personality Insights and Watson tone analyser to find patterns and trends from interviews and social media data.

The next challenge was to compare the different sports. For that we needed to come up with a relative metric that we could use to fairly stack up the tennis greats with the likes of Lewis Hamilton or Tiger Woods. One method we used for this when looking at reaction times across sports, was to identify the number of times a particular athlete was mentioned in a document also containing key words linked to responsiveness, whether that was in their career or in the duration of a race, match or round. This gave us a measure of the significance of a certain attribute to each of the sports and whether it had a positive and negative connotation with it.

As we know, cognitive computing is only as good as the data behind it. So it was important to bear in mind the data sources used. For interview data from tennis players, for examples, the pre- and post-match interview may not have been a true representation of that particular individual. Equally so, not all professionals contribute their own thoughts to their social media feeds. This is why it was so important that the process of finding insights was a collaborative effort between man and machine.

Our analysis gave some fantastic insight into the corpus of unstructured data. In addition to overarching trends and patterns, WDS also made it easy to drill down deeper into the data, allowing us to extract specific examples demonstrating the identified trends. Sometimes Watson indicated patterns that hadn’t yet been seen in the statistics. At other times, the statistical data supported the cognitive insights. And on occasions, the cognitive analyses even challenged conventional ideas of greatness.

In this Summer of Sport how do elite sports people find their advantage? #FindTheAdvantage

Although our analysis uncovered some exciting findings, the topic remains up for debate. In the coming week and throughout The Championships we will partner with Sky Sports experts to explore the Wimbledon greats in comparison to some of our other sporting favourites. Watch these six short discussions between former Wimbledon player and Sky pundit Mark Petchey and a host of sports experts from football, golf, rugby and F1. See what the experts made of the stats and Watson insights on durability, the importance of reactions and athletes ability to control emotion. Could the England squad take any advice from our Wimbledon champions when it comes to keeping their cool in Russia under the pressure of taking penalties?

Read the articles and watch the discussion with Sky Sports experts or discover how IBM helps Wimbledon to #FindTheAdvantage as the official technology partner of The Championships.

Get involved and contribute to the debate on social channels. Follow @IBM_UK_News and @IBMSports on Twitter for the latest #FindTheAdvantage and IBM@Wimbledon content.

For anyone interested in getting up and running with Watson services, sample code is available showing how to use Watson Discovery Service and Watson Personality Insights. Both services are available to try for free. Discovery Service comes with a data set of news sources that are updated continuously.

An award winning campaign!
The team at IBM and their campaign partner Ogilvy have been recognised at the DMA Awards, winning Gold in the Technlogy category for the #FindTheAdvantage campaign!

 

More Innovation stories

Building the IBM Emotive Droid

Animating emotion. This is a project to show of the use of affective computing (Emotional AI) in the Watson suite, which is IBM’s collection of cloud-based AI API’s. We hooked this into The Waston SDK for Unity, which allowed us to use this as a 3D Environment. The goal here was simple: to create an […]

Continue reading

Call for Code Finalists

Call for Code This year, IBM, in partnership with the American Red Cross, the UN, the Linux Foundation and many more, launched the Call for Code. Developers have revolutionised the way people live and interact with virtually everyone and everything. Where most people see challenges, developers see possibilities. The Call for Code is a multi-year, […]

Continue reading

IBM Emerging Technologies UK wins TechConnect 2016

This year IBM Emerging Technologies UK submitted 10 out of 86 entries for TechConnect. TechConnect is a Europe wide internal IBM annual competition for individuals showcasing their work to senior technical leaders and decision makers. This years winning entry, “Showcasing our academic research”, was one of the entries from the UK Emerging Technology Team. It is a web application […]

Continue reading