Credibility Determination Using Causal Remark Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for determining the credibility of information from search engines and question-answering systems on the Internet face challenges in accurately verifying the credibility of information, as they often rely on attributes of information senders that are difficult to obtain accurately or require user intervention to determine credibility.
Innovation Solution
A computer-implemented credibility determining system that uses causal relation knowledge to classify remarks based on time and position constraints, retrieving and analyzing remarks that match the input information to determine its credibility by categorizing them as causes, results, or contradictions, thereby providing a more accurate credibility assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a system uses attributes of information senders to determine credibility, then the determination process is simplified, but the accuracy of credibility determination deteriorates because accurate attributes can be obtained only in very limited situations
Solution Approach 1:
The patent introduces an intermediary mechanism (remark analysis system) that mediates between the information and the user. Instead of directly relying on sender attributes, the system retrieves and analyzes multiple user remarks related to the information, using these remarks as an intermediary evidence base to determine credibility objectively.
Solution Approach 2:
The patent replaces the manual/mechanical approach of checking sender attributes with an automated information processing system. The system automatically retrieves, classifies, and analyzes multiple remarks using computational methods, substituting human judgment with automated text analysis to improve both accuracy and efficiency.
2Device complexity
If a system presents materials for credibility determination to users, then the system complexity is reduced, but the productivity of information verification deteriorates because users must manually determine credibility
Solution Approach 1:
The system performs self-service by automatically completing the credibility determination process. Instead of merely presenting materials and relying on users to verify, the system autonomously retrieves remarks, classifies them by sentiment and relevance, analyzes the information, and outputs a credibility determination, making the verification process self-executing.
Solution Approach 2:
The system performs preliminary actions by pre-retrieving and pre-classifying multiple remarks before the user needs verification. The remarks are organized by sentiment (positive, negative, neutral) and relevance in advance, so when verification is needed, the analysis can proceed immediately without manual collection or classification work.
3Measurement precision
If a system retrieves and analyzes multiple user remarks with time and position constraints, then the accuracy of credibility determination is improved, but the device complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the complex credibility determination process into distinct modules: remark retrieval module, sentiment classification module (positive/negative/neutral), relevance analysis module, and credibility determination module. Each module handles a specific aspect, making the overall complex system manageable and maintainable through functional decomposition.
Solution Approach 2:
The system uses parameter changes by applying time constraints and position constraints as filtering parameters to retrieve relevant remarks. By changing these parameters (time range, geographic location), the system can adaptively adjust the remark set analyzed, improving accuracy without requiring a completely different system architecture.
Data Source
AI summary
A credibility determining system enabling highly accurate credibility determination of given information includes causal relation knowledge DB 90 and search scope constraint DB 88. Causal relation knowledge each includes a combination of cause and result parts, and time and position constraints associated with the causal relation. The credibility determining system further includes a query generating unit 92 retrieving a causal relation matching the input information and based on the time and position constraints stored in search scope constraint DB 88 in association with the retrieved causal relation, generating a query for retrieving remarks from mini-blog text DB 84, a text search unit 96 searching for related remarks from mini-blog text DB 84 using the query, and a display candidate selecting unit 100 classifying the searched remarks to expressions interpreted as causes or to results, determining credibility of the input information based on the classification result and outputting the determination result.