Social Media Influence Scoring via Topic-Specific Graph Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current social media monitoring systems face challenges in identifying influential users across diverse data streams, as existing influence metrics are not adaptable and require prior identification of influential users, making it difficult to analyze large datasets and detect influencers effectively.
Innovation Solution
A system that interfaces with social data sources, collects and enhances mentions, filters data, creates a conversation graph, and calculates influence scores to identify the most influential social media users based on their engagement and viral message exposure, independent of data stream size.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If existing influence metrics are used to identify influential users, then user influence can be measured, but the system requires prior identification of influential users and cannot adapt to different data streams or topics
Solution Approach 1:
The patent applies local quality by computing influence scores specific to each data stream and topic rather than using a single global influence metric. The system calculates topic-specific influence scores that adapt to different streams, allowing the same user to have different influence levels for different topics while maintaining a unified system architecture.
Solution Approach 2:
The patent implements dynamics by making the influence metric adaptive and dynamic rather than static. The system continuously updates influence scores based on current data stream characteristics and user interactions, allowing the metric to evolve with changing topics and data patterns without requiring system reconfiguration.
2Measurement precision
If all social media mentions are collected and analyzed, then comprehensive influence detection is achieved, but the huge quantity of data makes it very difficult to identify influential people
Solution Approach 1:
The patent applies the extraction principle by isolating and focusing analysis on specific data streams and topics rather than processing all social media mentions uniformly. The system extracts relevant mentions matching specific queries and computes influence scores only for these filtered datasets, significantly reducing processing requirements while maintaining detection accuracy.
Solution Approach 2:
The patent implements segmentation by dividing the large social media data into separate data streams and topics. Each stream is processed independently with topic-specific influence calculations, allowing parallel processing and reducing the computational burden of analyzing all mentions together while improving precision through specialized analysis.
3Measurement precision
If influence metrics are computed for all users in a data stream, then complete influence ranking is obtained, but the system cannot identify topic-specific influencers effectively
Solution Approach 1:
The patent applies local quality by computing influence scores specific to each data stream and topic rather than using a single global influence metric. The system calculates topic-specific influence scores that adapt to different streams, allowing the same user to have different influence levels for different topics while maintaining a unified system architecture.
Data Source
AI summary
The present invention relates to novel methods and implementing systems that afford a user the ability to analyze a certain stream of data, e.g., independent of size, and identify the people that influence the conversation.