Nielsen Launches Gracenote Audio On Demand for Advanced Podcast Search, Discovery

Nielsen has launched Gracenote Audio On Demand, a standardized and enriched dataset enabling powerful navigation, search and discovery of more than 37 million podcast episodes across all digital entertainment platforms. With this new offering, streaming music platforms, consumer electronics companies, Multichannel Video Programming Distributors (MVPDs) and automakers can create personalized listening experiences, allowing podcast and talk radio fans to connect to a broader range of personalities and topics than ever before.

Based on steadily increasing popularity, podcasts have entered the mainstream as a broad-reaching entertainment medium. According to Nielsen Scarborough, the audience for podcasting has been growing by 20% on average for the last six years. At that rate, the audience for podcasting could double by 2023.

“A big challenge for podcast listeners today is the ability to easily navigate all the audio-on-demand content across different platforms and services,” said Greg Gentschev, SVP of Product Management, Gracenote Music and Auto at Nielsen. “This is due to the sheer volume of content and lack of descriptive metadata and identifiers used to power search and discovery algorithms. With Gracenote Audio On Demand, we are applying the same rigor, methodology and approach to podcasts that currently underpins next gen search and discovery of today’s TV shows, movies and music.”

At launch, Gracenote Audio On Demand will have standardized podcast titles, descriptions and imagery across more than 900,000 podcast series. Each podcast series will be assigned a popularity score to help surface the most popular content, while the top series will leverage more descriptive information such as Category Hierarchy and Celebrity Links for more powerful universal search across platforms and cross-media linking capabilities.

–Popularity Score: Improves search and discovery capabilities by identifying and surfacing the most popular podcasts in a catalog.
–Category Hierarchy: Provides three levels of categories when classifying series and episodes to enable more engaging and unique discovery experiences.
–Celebrity Links: Allows listeners to identify verified celebrity links across content, providing rich discovery experiences.

Leveraging its world-class editorial team and powerful machine learning algorithms, Gracenote applies a detailed category taxonomy to both podcast series and episodes to make it easier for consumers to find the specific topics they’re interested in. The deep descriptive data and unique content identifiers offered by Gracenote Audio On Demand are subject to the same rigorous standards and quality control applied to Gracenote’s Global Video Data and Global Music Data products.

Other key benefits and features of Gracenote Audio On Demand include:

–Deduplicated & Normalized Data: Daily checks remove duplicate submissions and eliminate encoding issues.
–In-Depth Categorization: Standardized classifiers for series and episodes help surface more relevant content, enabling more engaging and unique discovery experiences.
–Standard IDs: Assigns a common Gracenote ID of reference for a podcast series across different platforms to support identification and cross-media linking.
–Parties and Celebrities: Allows users to identify verified celebrity links with role type, including host, guest and participant, enabling better linking than text-based approaches.
–API, SDK and Full Feed Access: Tap into data via the API, SDK or Full Feed for flexible implementation options.

————————————————

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.

%d bloggers like this: