# How Facebook Uses User Feedback to Improve Search Results

> A method for improving search engine accuracy by letting users manually rate search results, then using those ratings to automatically adjust how the search algorithm ranks future results.

- **Patent:** US 9398104
- **Original title:** Ranking test framework for search results on an online social network
- **Owner:** Facebook Inc
- **Granted:** 2016
- **Status:** Active
- **Times cited:** 0
- **Field:** software, ai_ml, ecommerce

## What it does

This patent describes a feedback loop for search algorithms within a social network. When a user performs a search, the system presents results that are personalized based on the user's connections in a social graph. The user then manually assigns scores to these results. The system uses these user-provided scores to calculate a 'discounted cumulative gain'—a mathematical metric that measures how well the search algorithm ordered the most relevant items at the top. The algorithm then updates its internal ranking logic to better prioritize similar results for future queries.

## What it does NOT cover

- Does not cover search ranking systems that rely solely on automated click-through rates rather than explicit user-provided scores.
- Does not cover general search engines that operate without a social graph or user-connection data.
- Does not cover the specific machine learning models used to perform the ranking, only the method of using user feedback to modify those models.

## The clever bit

It treats the user's manual rating of a search result as a direct input to re-weight the social graph's influence on future search rankings, effectively turning the user into a real-time trainer for the search algorithm.

## Real-world examples

1. Facebook search result feedback prompts
2. Internal search quality evaluation tools for social platforms
3. Personalized recommendation engines in social media apps

## Why it matters

As social networks grew, search became a primary way to navigate massive amounts of user-generated content. This patent represents the industry shift toward 'human-in-the-loop' optimization, where the platform treats its own users as data labelers to refine search relevance without needing expensive manual quality assurance teams.

## Frequently asked questions

### What does How Facebook Uses User Feedback to Improve Search Results cover?

A method for improving search engine accuracy by letting users manually rate search results, then using those ratings to automatically adjust how the search algorithm ranks future results.

### Who owns patent US 9398104?

Facebook Inc owns this patent, granted in 2016.

### When does this patent expire?

This patent is expected to expire on July 19, 2036, when the invention enters the public domain.

### What problem does this patent solve?

As social networks grew, search became a primary way to navigate massive amounts of user-generated content. This patent represents the industry shift toward 'human-in-the-loop' optimization, where the platform treats its own users as data labelers to refine search relevance without needing expensive manual quality assurance teams.

### What does this patent NOT cover?

Does not cover search ranking systems that rely solely on automated click-through rates rather than explicit user-provided scores.

**Full plain-English explainer:** https://patentbrief.org/patent/us/9398104/facebook-ads-manager

**Original patent:** https://patents.google.com/patent/US9398104

---

_Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._