Crowd Typing via Influence Hierarchy Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods lack effectiveness in accurately determining crowd type from large corpora of textual documents, such as social media posts, to inform targeted marketing or political strategies, as they fail to accurately measure influence and emotional resonance across diverse communities.
Innovation Solution
A system and method for determining influential scores of authors within a community by analyzing emotional content and echo patterns in textual data, using transfer entropy techniques to measure influence and graphing influence hierarchies, which allows for classification of crowd types based on influence scores and their logarithmic scaling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional text analysis methods are used to determine crowd type, then the analysis can be performed on large corpora of textual documents, but the accuracy in measuring influence and emotional resonance is insufficient
Solution Approach 1:
The patent transforms qualitative influence assessment into quantitative measurement by introducing specific parameters: echo count (number of times content is shared/discussed), echo intensity (emotional resonance measured through sentiment analysis), and influence score (composite metric combining multiple parameters). This parameter transformation enables precise measurement of influence while maintaining system manageability through mathematical modeling.
Solution Approach 2:
The patent introduces transfer entropy as an intermediary mathematical tool to measure the directional influence between different pieces of content and authors. This intermediary mechanism allows the system to objectively quantify influence relationships without requiring direct observation of social interactions, thereby improving measurement accuracy while avoiding the complexity of tracking all social dynamics.
2Measurement precision
If influence scores are calculated for all authors in a community, then crowd type classification becomes accurate, but the computational resources and time required increase significantly
Solution Approach 1:
The patent segments the community into hierarchical levels based on influence scores: highly influential authors (top percentile), moderate influencers, and regular participants. This segmentation allows the system to focus detailed analysis on key segments while using aggregated metrics for broader segments, thereby maintaining classification accuracy while reducing overall computational burden.
Solution Approach 2:
The patent implements partial action by calculating full influence scores only for a subset of authors (e.g., top content contributors or those with highest initial engagement metrics) while using approximation methods for the remaining authors. This approach achieves sufficient accuracy for crowd type classification without the excessive computational cost of calculating precise scores for every single author in the community.
3Measurement precision
If the system analyzes emotional content and echo patterns to determine influence, then the measurement of emotional resonance improves, but the complexity of data processing increases
Solution Approach 1:
The patent extracts specific emotional indicators from full text content by focusing on key sentiment-bearing words, phrases, and linguistic patterns rather than analyzing entire documents. This extraction approach captures essential emotional resonance information while dramatically reducing processing complexity compared to comprehensive semantic analysis of all textual data.
Solution Approach 2:
The patent employs a multi-functional text analysis module that simultaneously performs multiple tasks: sentiment detection, echo pattern recognition, influence scoring, and crowd type classification. By consolidating these functions into a unified system, the patent reduces overall complexity compared to using separate specialized systems for each function, while maintaining high measurement precision through coordinated analysis.
Data Source
AI summary
Systems and methods for providing hierarchy scores are described. Generally, influence scores for authors of a crowd may be determined based on emotional scores and echoing of time series data strings. One or more regression lines may be determined based on the influence scores to provide a raw hierarchy score and/or a central hierarchy score. Analysis and/or comparisons of the hierarchy scores may be used to classify the crowd type and output an influential score report.