liveBook · Manning

Implicit feedback

As explained in Hidden Influences

A user interaction inferred from behavior or non-explicit activity rather than directly stated as a preference.

If someone is shown videos about dogs and cats but interacts only with the dog videos, a platform may guess that dogs interest them more. Implicit feedback is the use of behavior—or the absence of an interaction—as a clue to a user’s preferences, rather than a preference they state directly. It is an inference, not a certainty. section 2.3.2

Platforms may treat time spent on an item, clicking a link, or the percentage of a video played as implicit signals. These differ from explicit feedback, such as a rating or a Like: behavior can suggest interest without the user deliberately declaring it. section 2.3.2

How Hidden Influences covers it

How deep it goes
Defines implicit signals, contrasts them with explicit ratings, and gives examples without detailing how signals are weighted.
Examples
Uses dog-versus-cat content, dwell time, link clicks, and video play percentage as preference clues.
What you can do after
Understand how platforms infer likely interests from observed interactions rather than stated ratings.
How it connects
Connects implicit feedback to recommender systems, machine learning, and explicit feedback.

Also explained in

Compare how 4 books explain implicit feedback →

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.