Nielsen’s Gracenote Launches Descriptive Metadata Package

Gracenote, subsidiary of video audience measurement and analytics group Nielsen, has released the first in a series of metadata-based products for content search and recommendation under its Advanced Discovery brand.

The firm is trumpeting the use of machine learning algorithms to derive contextually relevant metadata from content going beyond traditional basic descriptors such as genre and title, to include mood, theme, scenario and characters. The firm has kicked off with the first product in the new series called Gracenote Video Descriptors, designed to obtain a finer grained and deeper description of content as a foundation for more personalized video selection.

Gracenote cited as an example Game of Thrones which could be categorized under themes such as “Greed” and “Betrayal” and then Scenarios including “Power Struggle” and “Manipulation.” It could also be assigned to Mood elements like “Dark” and “Gripping”, while the characters could be classified from “Royalty” to “Dragons.”

So, under Scenarios, Gracenote data could be used to identify similar programs based on related descriptors such as “Sweet Revenge” or “Good versus Evil.” The firm contends that by understanding better what Game of Thrones is about and relating those attributes to other programs, Gracenote Video Descriptors can enable more deeply nuanced discovery that unearths content most likely to resonate with individual viewers.

It remains to be seen how successful that approach will be compared with conventional more superficial search methods, but it is notable that Gracenote does not believe machine learning can yet be relied on to extract the metadata unaided. The firm will still rely on a combination of its data scientists and editorial teams to oversee the process with machine learning operating almost in a subsidiary role as a tool to automate some aspects of the metadata generation.

Further releases from the Advanced Discovery suite will be rolled out in 2019, while Gracenote was demonstrating Video Descriptors alongside other entertainment data products at CES (Consumer Electronics Show) 2019 in Las Vegas.

Let us know what you think…

Log-in or Register for free to post comments…

You might also like...

Building On IP COTS

Transitioning to IP improves flexibility and scalability, both of which are achievable using COTS IT equipment. But can COTS solve every challenge? Or does broadcasting still have some unique and more demanding requirements that need further attention? In this article,…

The Move Towards Next Generation Platforms

Whenever I’m asked about my opinion on the transition to IP, I always state that the impact can’t be appreciated until its history is understood. This brings into context the need for broadcasters to educate and surround themselves wit…

Taming The Virtualized Beast

Without doubt, virtualization is a key technological evolution focus and it will empower many broadcast and media organizations to work differently, more efficiently and more profitably.

Color and Colorimetry – Part 3

The human visual system (HVS) sees color using a set of three overlapping filters, which are extremely broad. As a result, the HVS is completely incapable of performing any precise assessment of an observed spectrum.

Color and Colorimetry – Part 2

At one time the only repeatable source of light on Earth was the sun. Later it was found that if bodies were made hot enough, they would radiate light. Any treatment of illumination has to start with the radiation from…