IBM and the GRAMMYs

Powering Music’s Biggest Night
with a hybrid cloud approach from IBM

IBM and the GRAMMYs

video play button

Powering Music’s Biggest Night with a hybrid cloud approach from IBM

Thousands weighed in on a variety of debate topics with the help of Artificial Intelligence from IBM.
Watson’s world-class natural language processing assessed the persuasiveness of arguments, identified key points, and generated a complete narrative that reflects the wisdom of the crowd.

GRAMMY Debates with Watson

The Recording Academy® is on the journey to hybrid cloud, developing modern containerized applications – like GRAMMY Debates with Watson – on Red Hat® OpenShift®, capable of running on any cloud, public or private, from any vendor.

GRAMMY Awards®, built on the IBM Cloud

The digital experience for Music’s Biggest Night® has moved to the IBM Cloud®, which offers security and agility to scale the delivery of GRAMMY® Backstage to more than 7 million fans worldwide.

Key point analysis

How it works

Watson uses the latest innovations in natural language processing to identify the most significant key points and generate coherent narratives.

For “That’s Debatable,” Watson analyzes every submitted argument to determine if the content is for or against the position statement. Watson also removes submissions deemed irrelevant, such as those that are off-topic, or those that are deemed neutral – neither supporting nor contesting the statement.

Watson evaluates the quality of each submitted argument and identifies potential key points by grading and filtering high-quality arguments. It disregards potential key points that are too long, too emotional in tone, are incoherent or include redundancies. The arguments matched to each key point are sorted by the their argument quality and by the confidence in the matching.

The ranking of the quality is based on the machine learning model, which was trained on human assessments of over 30,000 arguments. There is a general correlation between the argument quality score and factors including grammar, clarity and repetition.

Watson now identifies how many arguments support each of the potential key points. It then selects a small set of key points that are diverse and cover the majority of arguments submitted.

Finally, Watson selects the key points cited most often in the submissions. For each key point, a small subset of the strongest arguments that support that key point is selected. Those key points and arguments are then used to formulate coherent, salient narratives — one arguing the pro side of the debate, the other arguing the con side.

Try it yourself

Submit an argument for or against one of our debate topics and then see how your powers of persuasion stack up against others.

Behind the debates

The journey to hybrid cloud and AI

GRAMMY Debates with Watson uses natural language processing (NLP) to classify, assess and summarize key points from thousands of arguments. As part of the Recording Academy’s journey to hybrid cloud, the application is built on Red Hat OpenShift, capable of running securely on any cloud, from any vendor.

Red Hat
OpenShift on
IBM Cloud

Accelerates development; consistently executes across all clouds.

NLP with

NLP with

Understands pros, cons and the quality of every argument.



Delivers world-class protection for an uncertain world.