[ad_1]
Pinterest provided insight into how its algorithm works and warned of the risks of over-reliance on user engagement. The platform highlighted that over-reliance on engagement to rank content can result in a negative user experience, and suggested non-engagement signals as a solution.
To encourage other companies to follow suit and help “build a more inspired internet,” Pinterest published a new document titled “Field Guide to Non-Engagement Signals.”
Why we care. By better understanding how Pinterest’s algorithm works, brands can determine which metrics to prioritize to ensure greater visibility for their content.
What are disengagement signals? Disengagement signals are generated from two primary sources:
- In-app surveys: These give users the opportunity to provide direct feedback about the platform. For example, Pinterest may conduct surveys within the app to collect user insights.
- Independent ratings of content quality: These are usually generated by manual labeling.
In addition to balancing engagement signals when ranking content, non-engagement signals allow Pinterest to align with its values. For example, Pinterest’s commitment to inclusivity is supported by signals of disengagement. When users specify preferences related to body type, hair pattern, or skin tone in their feed, Pinterest can prioritize relevant content accordingly.
Field guide. Pinterest partnered with UC Berkeley and the Integrity Institute to create the Field Guide to Non-Engagement Signals in an effort to help platforms create better user experiences. Pinterest noted that the goal of the guide is simply to help platforms make informed decisions when it comes to using disengagement signals, rather than telling them what to do.
Key learning points. Based on practical industry knowledge, the field guide provides several practical applications for product development, including:
- How to tune into emotional well-being.
- Using Genative AI to Scale Content Quality Signals.
- Improving user retention.
What Pinterest says. Leif Sigerson, Pinterest Sr. Data Scientist, and Wendy Matheny, Pinterest Sr. Lead Public Policy Manager, said in a blog post:
- “User engagement is a crucial signal used by Pinterest and other online platforms to determine what content to show users. However, it is well known that optimizing purely for user engagement can surface content that is low quality (e.g. clickbait) or even harmful.”
- “Our CEO, Bill Ready, explained that if we’re not careful, the ranking of content could reveal the ‘car crash we can’t look away from.’ Do you want to see another one?” The vast majority of people will say, ‘Gosh, no.'”
- “Disengagement signals are a critical part of ensuring we don’t optimize for ‘the car crash we can’t look away from.’”
Get the daily newsletter marketers trust.
Deep dive. Read Pinterest blogging complete or download a PDF copy of the field guide For more information.
[ad_2]
