Social Network Influence Score Calculation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing online social networks struggle to accurately rank members based on their influence within the network, as current methods like profile views do not effectively measure a member's overall influence, especially in professional contexts.
Innovation Solution
Calculating an influence score by combining centrality and expertise scores, where centrality is determined using algorithms like eigenvector centrality and Katz centrality, and expertise is based on skills, education, and employment data, with coefficients adjusting the scores to reflect network impact and professional standing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If profile views are used to rank members, then the ranking process is simple, but the accuracy of measuring member influence is insufficient
Solution Approach 1:
The patent transforms the single parameter of profile views into multiple parameters including centrality score (based on network position and connections) and expertise score (based on skills and knowledge), then combines these parameters with different coefficients to create a comprehensive influence score that accurately measures member influence
Solution Approach 2:
The patent creates a composite influence score by combining multiple distinct components (centrality score from network analysis and expertise score from profile data) into a unified measurement metric, similar to how composite materials combine different substances to achieve superior properties
2Measurement precision
If a comprehensive influence score combining multiple factors is calculated, then the accuracy of influence measurement is improved, but the computational complexity increases
Solution Approach 1:
The patent divides the complex influence measurement task into separate modular components: a centrality score module that analyzes network connections and position, an expertise score module that evaluates skills and knowledge from profile data, and a combination module that integrates these scores with configurable coefficients, making the system manageable and adaptable
Solution Approach 2:
The patent creates a multi-functional influence scoring system that can simultaneously evaluate different aspects of member influence (network centrality, expertise, connections) using a unified framework, allowing the same system to serve multiple ranking and recommendation purposes
Data Source
AI summary
Techniques for ranking members based on an influence score are described. For example, an influence score process can access, from a database in an online social network, member data of a first member in response to receiving a ranking request of the first member. Additionally, a contribution factor for each first-degree connection of the first member can be determined. A centrality score for the first member can be determined based on the contribution factor for each first-degree connection of the first member. Moreover, an expertise score for the first member can be determined based on the member data of the first member. Furthermore, an influence score of the first member can be calculated based on the centrality score and the expertise score. Subsequently, a user interface is configured to cause a presentation, on a display of a device, of the ranking of the first member based on the influence score.