Skip to main content

Overview

User Signal Service (USS) is a centralized online platform that supplies comprehensive data on user actions and behaviors on Twitter. This information encompasses both explicit signals, such as favoriting, retweeting, and replying, as well as implicit signals, including tweet clicks, video views, profile visits, and more.
USS gathers signals from various underlying datasets and online services, processing them into uniform formats for consistency across the recommendation pipeline.

Signal Types

Explicit Signals

Explicit signals represent intentional user actions that directly express user preference:

Favorites

User clicks the like button on tweets

Retweets

User shares tweets to their followers

Replies

User responds directly to tweets

Bookmarks

User saves tweets for later viewing

Shares

User shares tweets via external channels

Quote Tweets

User retweets with added commentary

Implicit Signals

Implicit signals capture user behavior that indicates interest without explicit engagement:

Tweet Clicks

User clicks to view tweet details

Video Views

Video playback duration and completion

Profile Visits

User navigates to author profiles

Impressions

Tweets displayed in user timeline

Dwell Time

Time spent viewing content

Scrolls

Scroll patterns and depth

Data Processing Pipeline

Standardization

USS ensures consistency and accuracy by:
  1. Collecting signals from various underlying datasets and online services
  2. Processing raw signals into uniform formats
  3. Validating signal quality and consistency
  4. Distributing standardized signals to downstream systems
Standardized source signals are utilized in both candidate retrieval and as machine learning features for ranking stages.

Use Cases

USS signals help identify relevant candidates from Twitter’s billion-scale corpus by understanding user preferences and historical behavior patterns.
Signals are transformed into features for training and inference in ranking models, providing rich context about user-tweet interactions.
Recent signals enable dynamic personalization of timelines and recommendations based on current user interests.
Historical signals serve as training labels for supervised learning models across the recommendation pipeline.

Signal Quality

USS maintains high signal quality through:
  • Deduplication: Removing duplicate events
  • Validation: Ensuring signal integrity and format compliance
  • Filtering: Removing spam and invalid actions
  • Normalization: Consistent timestamp and identifier formats
Signal quality directly impacts recommendation quality. USS applies strict validation to ensure only high-quality signals reach downstream systems.

Integration with Data Pipeline

USS integrates with other components in the data pipeline:
1

Unified User Actions

Consumes raw action events from the UUA stream
2

Signal Processing

Processes and standardizes signals for downstream use
3

Feature Generation

Provides signals to the Aggregation Framework for feature computation
4

Candidate Retrieval

Supplies signals for retrieval algorithms (SimClusters, TwHIN, UTEG)

Unified User Actions

Source of raw user action events

Retrieval Signals

How signals are used in candidate sourcing

Aggregation Framework

Transforms signals into aggregate features

Build docs developers (and LLMs) love