liveBook · Manning

EdgeRank

As explained in Hidden Influences

Facebook's early feed-ranking algorithm that weighted post recency and user interaction relationships to estimate relevance.

When a feed collects updates from many friends, finding the ones that matter can mean scrolling past people you barely know. Facebook introduced EdgeRank in 2007 to rank friends’ posts by personalized relevance instead of reverse chronology. section 1.2.2

EdgeRank used straightforward weighting: newer posts and posts from people a user interacted with more often received priority. That preference could feed back on itself: seeing more updates from someone could create more chances to interact with them. Unlike later platform algorithms, EdgeRank used a simple, understandable weighting formula. section 1.2.2

Interaction and relevance

Someone who messages a friend daily might want more updates from that friend than from someone they rarely interact with; EdgeRank gave the more frequently interacted-with friend greater weight. section 1.2.2

Figure 1.3 Various social media models. In the Subscription model, the content is seen only by users who explicitly follow the content producer, with no options or resharing. In the Network model, users can also reshare content from users they follow, enabling the distribution of content outside of the immediate network. Finally, in the Algorithmic model, an algorithm can add content to users’ feeds, even with no direct connection to the content itself or its author.

The figure contrasts subscription, network, and algorithmic feeds, placing personalized ranking in the wider shift toward algorithmically selected content. section 1.2.2

How Hidden Influences covers it

How deep it goes
Explains recency and interaction weighting and identifies a possible feedback loop.
Examples
Compares updates from a friend messaged daily with updates from someone rarely contacted.
What you can do after
Understand how recency and interaction weights can shape a personalized feed and reinforce interaction patterns.
How it connects
Connects recommender systems, PageRank, and feedback loops.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Hidden Influences. The section links point to the parts of the book it draws on.