LinkedIn now consider Dwell Time into its algorithm

Last updated on May 22nd, 2021 at 06:37 am

Dwell time will now be considered when content is ranked in the LinkedIn feed. How will your LinkedIn posts be affected? Let’s know more about it.

What is the working of LinkedIn feed Ranking?

A LinkedIn feed is a place where the users post ideas, posts, news, etc in the form of short-text, article, photo, or video. 

The current ranking method has two main checks:

• the First Pass
• the Candidate Generation layer

This lightweight algorithm filter identifies top candidate updates into the news feed of the user but the current order has a missing fine-tuned ranking among the top candidates, whose post will appear first?

The LinkedIn AI Team always focus to increase the relevance of the content in their feed. This is stated by considering the effect of viral actions in downstream and/or upstream posts.

The downstream effect is generated by the amount of re shares it gets.

Comments on the post, boost the upstream effect by providing feedback to the author.

To achieve better feed display, machine learning models are trained to predict some quantities for each potential click and viral action:

• P(action) = Probability of the Viewer taking this action on the update
• E[downstream clicks/virals | action] = Expected downstream clicks/virals if the viewer takes this action
• E[upstream value | action] = Expected upstream value to the author if the viewer takes this action

On this basis, LinkedIn is trying to main a healthy feed ecosystem by performing a point-wise ranking of all the candidate updates.

Significance of Dwell Time

There are shortcomings when an algorithm relies on click and viral actions for predictions.

For instance, passive consumers visit the feeds frequently but they rarely involve in the click and viral action.

Click and viral actions are binary in nature which also contributes to the limitation.

All the above measures have a missing element, which is, “the amount of time spent by a user on the post after committing certain action.”

To compensate for the shortcomings, the idea of DWELL TIME got emerged to check if it can contribute to improving feed ranking.

What is Dwell Time?

According to LinkedIn:

At a high level, each update viewed on the feed generates two types of dwell time. First, there is dwell time “on the feed,” which starts measuring when at least half of a feed update is visible as a member scrolls through their feed. Second, there is dwell time “after the click,” which is the time spent on content after clicking on an update in the feed.

Rest is Maths and deep AI concepts which you can read from the source blog by LinkedIn Engineering.

How to increase the Dwell Time of LinkedIn posts?

Every new update generates new challenges for the content creators and marketers. This update is focused on the amount of time one spends on the post. 

Making engagement focused posts will lead you nowhere if the users are not consuming your posts for a long duration. Remember the line and KEEP ROCKING on LinkedIn.

Till next blog, you can check out previous updates of my page.

Please Subscribe to my newsletter for getting more such updates.