LinkedIn Expands Engagement Signals to Higher Personalize User Feeds

Have you ever noticed a change in your LinkedIn engagement of late? Perhaps you’re seeing more posts from the identical people repeatedly, otherwise you’re getting fewer notifications?

There’s a reason for that. As outlined by LinkedIn expert Richard van der Blom, LinkedIn’s been tweaking its algorithm and notifications of late, which has significantly altered some points of the way it distributes posts, and shows people what they’re more likely to have interaction with.

In accordance with van der Blom’s most up-to-date evaluation:

• LinkedIn is showing you more content from the people and Pages you engage with most
• LinkedIn is putting more give attention to hashtag engagement to spotlight relevant topics to users
• LinkedIn’s reduced notifications for certain actions
• Posts are actually seeing more reach over time, versus gaining probably the most traction on the primary day (van der Blom says that posts are actually getting much more traction on the second and third day after posting)

So why is that this happening?

In accordance with a recent overview from LinkedIn, it’s recently updated its algorithm to consider more engagement signals, including how users interact with hashtags, who they engage with within the app, and even what they interact with, by way of individual posts.

As explained by LinkedIn:

“Our Homepage Feed produces billion-record datasets over thousands and thousands of sparse IDs each day. To enhance the performance and personalization of the feed, we’ve got added the representation of sparse IDs as features to the suggestion algorithms which power these products.”

Which is a technical way of claiming that it’s added more signals into the combination, with “sparse IDs” on this context referring to hashtags, users, and posts, amongst other interactions including Likes and shares. Indeed, LinkedIn says that it’s increased the parameters for its feed suggestion architecture by 500x.

“Our focus is on transforming large corpus sparse ID features into embedding space, using embedding lookup tables with a whole bunch of thousands and thousands of parameters trained on multi-billions of records. Embeddings represent high-dimensional categorical data in a lower-dimensional continuous space, capturing essential relationships and patterns inside the data while reducing computational complexity. For instance, members who share preferences or often interact with the identical kind of content or the same group of other members are likely to have similar embeddings, leading to a smaller distance within the embedding space. This capability enables the system to discover and recommend content that’s contextually relevant or aligns with member preferences.”

That’s numerous words, yes, and technical papers usually are not ideal for attempting to unravel what they practically mean for you and I. But essentially, you’re likely seeing posts from smaller groups of individuals, and on more focused topics, because that’s what you’re likely to have interaction with most, and LinkedIn’s algorithm now has more measures to consider, so as to predict likely engagement.

Which should mean that your LinkedIn feed is more interesting, and more aligned to your actual interests. Which can or will not be ideal for discovery, because numerous people engage with their colleagues, former and current, versus their current areas of interest, however the weighting of hashtag engagement, for instance, will probably be critical on this respect, ideally presenting a balance of individuals directly and the topics of most relevance to you right away.

But yes, you could see more of the identical people than you used to in your feed consequently.

The answer? Engage with more hashtags, add your comments to relevant discussions, and participate within the app. The more you interact, the more signals you send to the algorithm about your interests, and it’s now more attuned than ever to your specific focus subjects.

And it’s clearly doing something right. Sharing of original content on LinkedIn increased by 41% year-over-year in 2022, while the platform continues to report “record levels” of engagement inside parent company Microsoft’s quarterly performance updates.  

As more people search for an alternative choice to Twitter, and the changes being implemented by Elon Musk, plainly LinkedIn has been a key beneficiary, while its continued algorithm updates are also driving more engagement, and bringing users back more often.

As such, specializing in key topics of interest may very well be the important thing to optimizing your LinkedIn experience, while from a posting perspective, it’s also price underlining the worth of community engagement, and constructing on this where you possibly can, by replying to comments, using relevant hashtags, sharing topical updates, etc.

There’s no secret code, as such, to cracking the algorithm, but LinkedIn now knows more about who’s interested by your content, and it’s increasingly prone to show it to them in-stream.