liveBook · Manning

Reranking

As explained in Hidden Influences

An optional recommendation-system stage that adjusts an already ranked item list before results are delivered.

A feed can rank several posts from one creator highly, then adjust their order so they do not all appear together. Reranking is an optional step that makes minor changes to an already ranked list before delivery. section 2.2 section 2.2.4

Platforms can use reranking to:

  • Separate posts from the same creator or avoid placing ads next to each other, reducing feed fatigue or the impression of too much promotion. section 2.2.4
  • Boost posts from verified public-health services, or downrank posts linking to competitors. These adjustments can reflect platform priorities, not just predicted user interest. section 2.2.4

Changing the mix of posts

In a study, researchers downranked posts expressing positive or negative sentiment for different user groups. The observed changes in users’ own posts were tiny, and the study could not establish causation. section 7.1

Figure 2.1 A bird’s-eye overview of a recommender system. Recommendations are not the output of a single operation; rather, they are the results of multiple interlinked operations. Candidates are generated from the universe of all possible content—for example, by picking posts from users that are followed. Later, candidates are filtered to restrict the pool to a more manageable number. At this stage, the content gets actively sorted by the Heavy Ranker in accordance with a predefined metric. Such a ranked list can be adjusted, if needed, before being delivered to the users, whose engagement is recorded. Platform policies influence the filtering and post-processing steps, for example, by limiting the amount of content from the same author.

See where reranking sits between heavy ranking and delivery, alongside the other linked steps in a recommender system. section 2.2

How Hidden Influences covers it

How deep it goes
Explains rule-based adjustments and score boosts or penalties, without detailing their implementation.
Examples
Uses creator and ad ordering, public-health boosts, competitor downranking, and a sentiment-based feed experiment as examples.
What it assumes
Builds on the idea of a ranked list produced by heavy ranking before results are delivered.
What you can do after
Understand how post-ranking adjustments can change what users see and distinguish measured effects from causal claims.
How it connects
Connects reranking to recommender systems, heavy ranking, filtering, candidate generation, and platform policy.

Also explained in

Compare how 9 books explain reranking →

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.