PageRank Mean Absolute Sum for Dynamic Noun Importance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing text analysis methods, such as TF-IDF, struggle to accurately calculate the changing importance of words over time and their external influence in text data, particularly in news articles, which limits their ability to identify keywords and social impacts effectively.
Innovation Solution
The introduction of the noun frequency-link frequency (NF-LF) technology, which uses graph theory to calculate a PageRank Mean Absolute Sum (PR-MAS) score, accounting for the frequency of nouns and links between them, to quantify social impact and external influence across a society.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If TF-IDF technology is used to calculate word importance, then keyword extraction can be performed, but the ability to calculate changing importance over time and external influence is limited
Solution Approach 1:
The patent applies dynamics by transitioning from static TF-IDF scoring to dynamic PageRank-based importance calculation that evolves over time. The system continuously updates noun importance scores based on temporal patterns and link frequency changes, enabling the detection of time-varying social impact while maintaining measurement precision through iterative refinement of importance metrics.
Solution Approach 2:
The patent changes parameters by introducing temporal dimensions and link frequency as new variables alongside traditional term frequency. The system modifies the importance calculation by incorporating time-based weight adjustments and connection strength metrics, transforming the static TF-IDF parameter set into a dynamic multi-parameter model that captures evolving social impact.
2Adaptability or versatility
If NF-LF technology with graph theory is used, then time-varying importance and external influence can be captured, but computational complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the complex graph processing into distinct phases: noun extraction, link frequency calculation, PageRank computation, and social impact scoring. Each phase handles a specific aspect of the analysis independently, reducing overall computational complexity while maintaining the ability to capture time-varying importance and external influence through structured modular processing.
3Measurement precision
If PR-MAS calculation is performed on continuously collected text data, then social impact can be quantified, but data processing time increases
Solution Approach 1:
The patent applies preliminary action by pre-processing text data to extract nouns and construct the base graph structure before PR-MAS calculation is needed. The system prepares noun frequency statistics and link frequency relationships in advance, so that when new text data arrives, the computationally intensive PageRank and social impact quantification can be performed quickly using pre-established structures rather than building everything from scratch.
Data Source
AI summary
One or more embodiments relate to a text data-based method and system for deducing a social impact, which calculates a digitized variable, a Page Rank Mean Absolute Sum (PR-MAS), for identifying a change over time in the importance of nouns in regularly collected text data.