Sentiment Analysis Knowledge Base Auto-Update

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Sentiment analysis systems face challenges in accurately analyzing opinions from social media due to the dynamic nature of language, with new terms and expressions emerging frequently, making it difficult to maintain an up-to-date knowledge base without the need for lengthy re-training processes.

Innovation Solution

A method for updating a sentiment analysis system's knowledge base by extracting and scoring new terms from social media messages, using their frequency of occurrence and sentiment context to determine their relevance and accuracy, thereby automatically adding or removing terms from the knowledge base.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If the knowledge base is updated frequently to include new terms from social media, then the accuracy of sentiment analysis is improved, but the system complexity and processing time increase

Engineering Contradiction:

Improveaccuracy of sentiment analysisVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by continuously monitoring and extracting new terms from social media messages, calculating their sentiment scores in advance, and preparing them for knowledge base integration before they are needed for analysis, thus reducing processing complexity during actual sentiment analysis operations

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system serves itself by automatically detecting new terms, calculating their sentiment scores based on message context, and updating the knowledge base without requiring external intervention or manual curation, thereby maintaining accuracy while managing complexity autonomously

Inventive Principle:

Principle #25Self-service

2Measurement precision

If the knowledge base is updated frequently to include new terms from social media, then the accuracy of sentiment analysis is improved, but the time required for updates increases

Engineering Contradiction:

Improveaccuracy of sentiment analysisVSAvoidtime required for updates

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system maintains continuous useful action by continuously monitoring social media messages and automatically updating the knowledge base in real-time or near-real-time, eliminating gaps between language evolution and system adaptation, thus improving accuracy without significant time loss

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The system performs preliminary extraction and scoring of new terms as they appear in social media messages, preparing them for immediate integration into the knowledge base, which reduces the time required for updates by having terms ready in advance

Inventive Principle:

Principle #10Preliminary action

3Reliability

If manual curation of the knowledge base is performed to ensure accuracy, then the reliability is improved, but the productivity decreases

Engineering Contradiction:

Improvereliability of sentiment analysisVSAvoidproductivity of knowledge base updates

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system performs self-service by automatically calculating sentiment scores for new terms based on their context in social media messages, eliminating the need for manual curation while maintaining reliability through algorithmic consistency and objective scoring mechanisms

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system uses feedback from the actual usage of terms in social media messages to automatically adjust and refine sentiment scores, ensuring reliability through data-driven validation while maintaining high productivity by eliminating manual review processes

Inventive Principle:

Principle #23Feedback

4Ease of operation

If the knowledge base is kept static to reduce processing complexity, then the ease of operation is improved, but the adaptability to new language usage decreases

Engineering Contradiction:

Improveease of operationVSAvoidadaptability to new language usage

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The system implements dynamics by making the knowledge base adaptive and evolving rather than static, automatically incorporating new terms and updating sentiment scores based on changing language usage in social media, thus maintaining ease of operation through automated processes while improving adaptability

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11755841B2Method for updating a knowledge base of a sentiment analysis system

Publication Date: 2023.09.12 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A mechanism is provided updating a knowledge base of a sentiment analysis system, the knowledge base being operable for storing natural language terms and a score value related to each natural language term, the score value characterizing the sentiment of the natural language term. Messages comprising natural language are received. Using content of the knowledge base, a decision is made as to whether at least one message of the received messages has a positive sentiment or a negative sentiment. A term is extracted from the message that is not present in the knowledge base. Based on a frequency of occurrence of the term in the received messages and the sentiment of the messages in which the term occurs, a score value of the term is calculated, and the term and the calculated score value are stored into the knowledge base.