> ## Documentation Index > Fetch the complete documentation index at: https://mintlify.com/twitter/the-algorithm/llms.txt > Use this file to discover all available pages before exploring further. # User Signal Service > Centralized platform for comprehensive user action and behavior data across Twitter ## 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: User clicks the like button on tweets User shares tweets to their followers User responds directly to tweets User saves tweets for later viewing User shares tweets via external channels User retweets with added commentary ### Implicit Signals Implicit signals capture user behavior that indicates interest without explicit engagement: User clicks to view tweet details Video playback duration and completion User navigates to author profiles Tweets displayed in user timeline Time spent viewing content Scroll patterns and depth ## Data Processing Pipeline ```mermaid theme={null} graph TD A[Multiple Data Sources] --> B[USS Collection Layer] B --> C[Standardization] C --> D[Uniform Signal Format] D --> E[Candidate Retrieval] D --> F[ML Features] D --> G[Ranking Models] ``` ## 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: Consumes raw action events from the UUA stream Processes and standardizes signals for downstream use Provides signals to the Aggregation Framework for feature computation Supplies signals for retrieval algorithms (SimClusters, TwHIN, UTEG) ## Related Components Source of raw user action events How signals are used in candidate sourcing Transforms signals into aggregate features