Sentiment Analysis Using Syntactic Dependency Trees
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies face challenges in effectively processing and visualizing textual data, particularly in determining sentiment from large datasets, as they often struggle with syntactic ambiguity and accuracy in sentiment scoring, which limits their ability to provide meaningful insights from textual news data and other forms of textual information.
Innovation Solution
The method involves receiving textual data, parsing it to generate syntactic dependency trees, determining sentiment scores based on these trees, and generating images to represent the sentiment, with statistical sampling and accuracy scoring to enhance the accuracy of sentiment analysis, allowing for visualization through a GUI.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional sentiment analysis methods are used on large textual datasets, then processing speed is maintained, but accuracy in determining sentiment scores deteriorates due to syntactic ambiguity
Solution Approach 1:
The patent segments the textual data processing into distinct stages: parsing textual data into syntactic dependency trees, identifying sentiment-bearing words and phrases within the parsed structure, determining sentiment scores for identified elements, and aggregating scores to produce overall sentiment analysis results. This segmentation allows each stage to be optimized independently, improving overall accuracy while managing complexity.
Solution Approach 2:
The patent introduces syntactic dependency trees as an intermediary structure between raw textual data and sentiment scoring. These trees serve as a mediating representation that captures the grammatical and semantic relationships among words, enabling more accurate sentiment analysis by considering contextual relationships rather than treating words in isolation.
2Measurement precision
If comprehensive sentiment analysis of all textual data is performed, then accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
The patent applies partial action by focusing sentiment analysis resources on specific sentiment-bearing words and phrases identified through parsing, rather than analyzing every word in the dataset equally. The system identifies and concentrates processing effort on elements that contribute most to sentiment determination, achieving high accuracy without exhaustive processing of all textual data.
Solution Approach 2:
The patent applies local quality by treating different portions of the textual data with different levels of analysis intensity. Sentiment-bearing words and phrases identified through syntactic parsing receive detailed sentiment scoring and contextual analysis, while other portions of the text receive less intensive processing. This differential approach optimizes the balance between accuracy and processing efficiency.
Data Source
AI summary
Described herein are improved systems and methods for overcoming technical problems associated with processing and visualization of textual data and natural language processing. In some examples, a method is provided for determining sentiment associated with big data analysis of database information. In some examples, textual news data (e.g., NEWS API, RSS, etc.) is received via a communications network from a plurality of data platforms. The textual news data is parsed, and syntactic dependency trees are generated therefrom. A sentiment score is derived for the parsed textual data corresponding to a word or phrase associated with the textual data, and an image is generated reflecting scored sentiment for the parsed textual data.