Social Network Ad Targeting via Influence Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for advertising on social networks lack efficiency in targeting users based on their interests and influence, leading to suboptimal ad placement and propagation.
Innovation Solution
A system and method that ranks users by their influence and similarity to advertiser-defined characteristics, using a bidding mechanism to assign ad opportunities to influential users, and propagates ads through a heat diffusion model across the social network.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users are targeted with advertisements based on profile page content, then ad relevance to user interests is improved, but advertising efficiency and reach are limited
Solution Approach 1:
The patent transitions from traditional profile-based targeting to influence-based targeting by introducing an influence score dimension. This score quantifies a user's ability to propagate advertisements through the social network, creating a new dimension for ad placement decisions that complements traditional interest-based targeting.
Solution Approach 2:
The system changes the parameter used for user selection from profile content characteristics to influence scores. By calculating influence scores based on network position and propagation potential, the system identifies users who can effectively spread advertisements, thereby improving advertising efficiency while maintaining relevance.
2Productivity
If advertisements are displayed to users with high influence scores, then ad propagation effectiveness is improved, but the cost or bid amount increases
Solution Approach 1:
The system performs preliminary calculation and ranking of user influence scores before the advertising campaign begins. By pre-identifying high-influence users and their propagation potential, advertisers can make informed bidding decisions and allocate budgets more efficiently, reducing the overall cost while maintaining effectiveness.
Solution Approach 2:
The patent implements a bidding mechanism where advertisers can selectively bid on portions of the user base (e.g., top 10% by influence score) rather than attempting to reach all influential users. This partial action approach optimizes the balance between propagation effectiveness and bid cost.
3Area of stationary object
If the entire social network is targeted with general advertisements, then ad reach is improved, but ad relevance to specific user interests decreases
Solution Approach 1:
The patent applies local quality by tailoring advertisements to specific user groups based on their influence scores and profile characteristics. Instead of uniform advertising across the entire network, the system creates localized ad placements that match user interests while leveraging their influence for broader propagation.
Solution Approach 2:
The system segments the social network user base into distinct groups based on influence scores and profile characteristics. This segmentation enables differentiated advertising strategies where high-influence users receive targeted ads that leverage their propagation capability, while maintaining overall network-wide reach through multi-tiered placement.
Data Source
AI summary
In one implementation, a computer-implemented method includes receiving at a server a request from an advertiser to target an ad to users of a computer-implemented social network, the request comprising data representing characteristics of the users that the advertiser desires to target. The method further includes ranking the users based on how similar the users' characteristics are to the received characteristics and an influence score for each user that indicates how influential the user is within the social network. The method also includes scoring the advertiser's request based on a bid from the advertiser for an opportunity to display the ad to one or more of the users and assigning the opportunity to display the ad to the one or more users based on a correlation between a score of the advertiser's request and one or more rankings of the one or more users.