Aggregated Sentiment Analysis for Threat Protection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies lack effective methods to analyze sentiment from publicly available opinionated data to predict threats, detect communication difficulties within organizations, and optimize inter-organizational communications.
Innovation Solution
A method for aggregating and analyzing sentiment from various communication artifacts using natural language processing, computational linguistics, biometrics, and text analysis to determine sentiment scores, which are then used to identify potential threats or communication issues between entity groups, enabling remediation actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sentiment analysis is performed on communication artifacts to identify threats and communication issues, then threat detection capability and communication optimization are improved, but system complexity and computational resources required increase
Solution Approach 1:
The system segments the sentiment analysis process into distinct functional modules: artifact mining module that collects communication artifacts, sentiment analysis module that processes the artifacts using NLP and text analysis, and threat detection module that identifies communication issues. This segmentation allows each module to be optimized independently while maintaining overall system reliability for threat detection.
Solution Approach 2:
The patent introduces intermediary components including a sentiment library that stores pre-defined sentiment indicators and communication patterns, and an aggregation module that consolidates sentiment scores from multiple artifacts. These intermediaries buffer the complexity between data collection and analysis, reducing the computational burden on the core threat detection logic.
2Measurement precision
If multiple analysis processes (NLP, computational linguistics, biometrics, text analysis) are used to determine sentiment scores, then measurement precision of sentiment is improved, but processing time and computational resources increase
Solution Approach 1:
The system implements a multi-pass analysis approach where not all analysis processes are applied to every artifact. The sentiment analysis module first performs quick text analysis using the sentiment library for common patterns, then applies more computationally intensive NLP and computational linguistics only to artifacts that require deeper analysis or show ambiguous sentiment, thus reducing average processing time while maintaining precision for critical cases.
Solution Approach 2:
The patent pre-processes and stores sentiment indicators, communication patterns, and entity relationships in the sentiment library before actual analysis occurs. This preliminary action allows the system to quickly match artifacts against known patterns during sentiment scoring, reducing real-time processing requirements while maintaining high measurement precision through pre-computed reference data.
Data Source
AI summary
A system for aggregating sentiment analysis of communications between a plurality of entity groups is provided. The system may include a plurality of entity groups. Each entity group may include one entity, two entities or a plurality of entities. The system may include a plurality of communications. Each of the communications may be transmitted from a first entity. A first entity group may include the first entity. The plurality of entity groups may include the first entity group. Each of the communications may be transmitted to a second entity. The second entity may be included in a second entity group. The second entity group may be included in the plurality of entity groups. The system may also include a sentiment score determination module. The sentiment score determination module may determine an aggregate sentiment score for the plurality of communications. The sentiment score may determine a communication threat level.