Social Network User Clustering via Interaction-Based Targeting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Content providers often fail to present relevant content to users due to limited information about user characteristics, leading to missed opportunities in targeting specific audiences with personalized digital media.
Innovation Solution
A social networking system identifies users who have interacted with advertisements related to a specific topic, forms clusters of users with similar characteristics, and assigns scores based on similarity, allowing for the selection of users likely to engage with relevant content.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If content providers use traditional demographic targeting methods, then content can be presented to typical consumers of media, but atypical consumers encounter irrelevant content and content providers miss opportunities to reach suitable audiences
Solution Approach 1:
The patent introduces interaction data as an intermediary element that bridges the gap between limited explicit user information and actual user characteristics. By using interactions with content items as a mediator, the system can infer user characteristics without requiring direct user input or extensive explicit information, thereby resolving the contradiction between having sufficient user information and maintaining simple targeting methods
Solution Approach 2:
The system implements feedback by using user interactions with content items to continuously refine and update user characteristic profiles. This feedback loop allows the system to improve content targeting effectiveness over time, converting previously implicit user characteristics into explicit, actionable information that enhances content delivery while reducing information loss
2Productivity
If content providers present content based on limited user information, then the system operation remains simple, but opportunities to present relevant content to specific user groups are missed
Solution Approach 1:
The system applies self-service by automatically collecting, analyzing, and utilizing user interaction data without requiring external intervention or complex manual analysis processes. The system serves itself by generating user characteristic information from its own operational data (interactions with content items), thereby improving content relevance while avoiding the complexity of external user research or manual profiling systems
Solution Approach 2:
The patent makes the interaction data collection and analysis system universal by using the same mechanism across different content types and user contexts. The interaction-based characteristic identification works consistently across various content categories and user behaviors, providing a multi-functional solution that improves content relevance for all user groups without requiring separate complex analysis systems for different scenarios
Data Source
AI summary
A social networking system presents users with a content items and ad requests, which may include targeting criteria specifying a topic. Interactions by users who were presented with an advertisement from an ad request including targeting criteria specifying the topic are stored by the social networking system and used to identify a cluster group of additional users having characteristics similar to characteristics of users who were presented with the advertisement from the ad request including targeting criteria specifying the topic and who interacted with the advertisement. The social networking system determines scores for additional users in the cluster group based on measures of similarity between the additional users and the users who were presented with the advertisement and who interacted with the advertisement. Based on the determined scores, the social networking system associates additional users in the cluster group with the topic.