liveBook · Manning

Indirect observation

As explained in Hidden Influences

Inference of a user's preferences from observed behavior rather than from explicitly stated preferences.

Recommender systems infer preferences from behavior—such as what people like or interact with—instead of asking them to list what they want. A social-media feed might prioritize newer posts and friends a user interacts with often. section 1.2.2

A feedback loop in the feed

Seeing a friend’s updates more often can create more chances to message them; those interactions may then help the system infer that their posts matter to you. 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.

Compare subscription, network, and algorithmic feeds: algorithmic feeds can include content even without a direct connection to its author. section 1.2.2

How Hidden Influences covers it

How deep it goes
Explains behavioral signals and a possible feedback loop, but leaves fuller treatment of feedback loops for later.
Examples
Uses social-feed ranking by post recency and interaction frequency to illustrate inferred preferences.
What you can do after
Understand how recommender systems infer preferences from behavior and how repeated exposure may reinforce interactions.
How it connects
Connects recommender systems and algorithmic ranking with 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.