Context-Aware Sentiment Analysis Using Group-Associated Terms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods are inefficient and impractical for extracting and tracking sentiments or opinions towards entities from large volumes of text documents, requiring manual examination and being limited by the subjective nature of sentiment analysis.
Innovation Solution
A system and method that utilize a sentiment dictionary with context-associated terms to calculate a sentiment score by screening text documents for occurrences of sentiment terms, incorporating context information through a processing platform that retrieves and analyzes text documents, and adapts the sentiment dictionary based on query contexts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual examination of text documents is used to extract sentiment, then measurement precision may be maintained through human judgment, but productivity is severely reduced due to the huge amount of information requiring analysis
Solution Approach 1:
The patent replaces manual mechanical examination with an automated computer-based system that uses text retrieval, text mining, and natural language processing to extract sentiments from documents. The system automatically identifies sentiment terms, determines their polarity, and calculates sentiment scores without human intervention, thereby dramatically improving productivity while maintaining measurement precision through structured computational methods.
Solution Approach 2:
The system enables self-service sentiment analysis by automatically retrieving text documents, identifying sentiment terms, determining their polarity, and calculating sentiment scores without requiring manual examination. The automated process serves itself by integrating multiple functions (retrieval, mining, analysis) into a unified system that operates independently, resolving the contradiction between speed and accuracy.
2Ease of operation
If conventional sentiment analysis methods are used, then ease of operation is maintained through simple processes, but adaptability deteriorates due to the subjective nature of sentiment analysis and inability to handle context variations
Solution Approach 1:
The patent applies local quality by associating sentiment terms with specific contexts and determining polarity based on the local context in which each term appears. Instead of applying a uniform sentiment analysis approach, the system adapts the polarity determination to the specific context (e.g., positive, negative, neutral) surrounding each sentiment term, thereby improving adaptability while maintaining ease of operation through automated context recognition.
Solution Approach 2:
The system implements dynamics by making the sentiment analysis process adaptive to different contexts. The polarity of sentiment terms is not fixed but is determined dynamically based on the context in which they appear. This dynamic approach allows the system to handle various contexts (positive, negative, neutral) automatically, improving versatility without complicating the operation for users.
3Reliability
If detailed manual examination is performed to ensure reliable sentiment extraction, then reliability is improved, but loss of time increases significantly due to the volume of documents requiring analysis
Solution Approach 1:
The patent applies preliminary action by pre-processing text documents through automated retrieval and text mining before sentiment analysis. The system prepares the data in advance by identifying and extracting relevant sentiment terms and their contexts, so that the actual sentiment scoring can be performed quickly and reliably. This preliminary preparation reduces the time required for detailed examination while maintaining reliability through systematic processing.
Solution Approach 2:
The system replaces time-consuming manual examination with automated computational processing. The computer-based system rapidly retrieves documents, mines text for sentiment terms, determines polarity, and calculates sentiment scores in a fraction of the time required for manual analysis, while maintaining reliability through consistent application of structured algorithms and context-aware processing.
Data Source
AI summary
A method for estimating a sentiment conveyed by the content of information sources towards an entity is presented. The sentiment is obtained with respect to a query context that may be specified, e. g. by specific terms or expressions, like a product or service name. A sentiment dictionary having a plurality of sentiment terms is provided, wherein each sentiment term has assigned a sentiment value, and at least one of said sentiment terms is associated to a group context. Text documents are screened for occurrences of sentiment terms that are associated to a group context corresponding to the query context. Calculating a sentiment score value is performed as a function of the occurrences of sentiment terms having a similar or same group context as the query context. The method may be carried out automatically without manual analysis of the actual semantic content of the text documents under consideration.