Sentiment Normalization Engine Corrects Social Network Bias
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Social media sentiment analysis is biased due to factors like user activity patterns, network characteristics, and timing, leading to inaccurate reflections of public opinion on events or topics.
Innovation Solution
A system and method for detecting, measuring, and normalizing sentiments on social networks by using a data collection engine to gather user activities and a sentiment analysis engine that accounts for biases in the social network, event nature, and user tendencies, providing a normalized sentiment score that reflects general public sentiment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sentiment analysis is performed on social network data, then real-time gauge of user views is obtained, but measurement accuracy deteriorates due to biases from user activity patterns and network characteristics
Solution Approach 1:
The patent introduces intermediary components including a normalization engine and baseline sentiment models that mediate between raw social network sentiment data and final sentiment measurements. These intermediaries adjust for biases by comparing user sentiments against normalized baselines that account for user activity patterns, network characteristics, and event-specific factors, thereby improving measurement accuracy without losing real-time capabilities
Solution Approach 2:
The system dynamically changes parameters by adjusting sentiment scores based on multiple factors including user activity levels, network characteristics, and event-specific contexts. The normalization process transforms raw sentiment measurements into adjusted scores that compensate for various biases, effectively changing the parameter values to reflect true public sentiment rather than artifacts of social media usage patterns
2Measurement precision
If normalization processes are applied to correct biases, then sentiment accuracy improves, but system complexity increases
Solution Approach 1:
The patent segments the normalization process into distinct modular components: a normalization engine, baseline sentiment models, and event-specific adjustment modules. Each component handles a specific aspect of bias correction independently, making the overall complex system manageable through functional segmentation and allowing for targeted optimization of individual modules
Solution Approach 2:
The system performs preliminary actions by pre-computing baseline sentiment profiles for users and events before actual sentiment analysis occurs. These pre-established baselines are stored and reused during normalization, reducing the computational complexity during real-time analysis while maintaining high measurement accuracy
Data Source
AI summary
A new approach is proposed that contemplates systems and methods to provide the ability to detect, measure, aggregate, and normalize sentiments expressed by a group of users on a certain event or topic on a social network so that the normalized sentiments truly reflect the sentiments of the general public on that specific event or topic. Additionally, the collected and measured sentiments of an individual user expressed on a social network can also be normalized against a baseline sentiment that reflects in order to truly reflect the individual user's sentiment at the time of his/her expression.