Contextual Sentiment Analysis for Multi-Competitor Texts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing sentiment analysis systems are not accurate in determining the sentiment of multi-competitor referenced texts, neglecting brand-specific comments and failing to provide reliable sentiment prediction for target brands within the context of competitors, leading to unusable tonalities for business strategies.
Innovation Solution
A method and system for contextual sentiment analysis using AI models to identify keywords, determine patterns, and calculate tonality scores for competitor and target entities within texts, allowing for precise sentiment determination and notification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing sentiment analysis systems are used to analyze multi-competitor referenced texts, then the analysis process is simple, but the accuracy of sentiment determination is poor
Solution Approach 1:
The patent segments the sentiment analysis process into distinct modules: text identification module, pattern determination module, placement identification module, and tonality score determination module. Each module handles a specific aspect of the analysis, improving overall accuracy while maintaining manageable system complexity through functional decomposition.
Solution Approach 2:
The patent introduces intermediary elements such as pattern lexicons, AI models, and tonality scores that mediate between the input text and final sentiment determination. These intermediaries enable more precise sentiment analysis by breaking down the complex task into measurable components.
2Measurement precision
If broad text identification is used to capture all competitor references, then the quantity of analyzed texts is high, but the precision of brand-specific sentiment analysis is low
Solution Approach 1:
The patent applies local quality by creating pattern lexicons specific to each brand and analyzing the placement of brand names within text patterns. This allows the system to maintain high brand-specific precision while processing a focused quantity of relevant texts, rather than analyzing all possible competitor references uniformly.
3Reliability
If conventional sentiment analysis is used without contextual understanding, then the processing speed is fast, but the reliability of sentiment prediction is poor
Solution Approach 1:
The patent performs preliminary actions by pre-defining pattern lexicons, training AI models with contextual data, and establishing placement patterns before actual sentiment analysis. This preparation enables the system to maintain high processing speed during operation while ensuring reliable sentiment predictions through pre-established contextual understanding.
Data Source
AI summary
Disclosed herein is method and system for contextual sentiment analysis of competitor referenced texts. The method comprises obtaining, by a system a plurality of texts and a lexicon comprising keywords indicating a competitor entity and a target entity. Further, identifying texts from the plurality of texts including the keywords. Furthermore, determining a pattern from a plurality of patterns in the texts using Artificial Intelligence (AI) models. Furthermore, identifying a placement of the competitor entity and the target entity in the texts using the AI models. Furthermore, determining for each of the texts, a tonality score indicating a tone towards the target entity based on the placement of the target entity and the pattern. Furthermore, determining a sentiment for each of the texts based on the tonality score. Finally, notifying the sentiment towards the target entity on a notification unit.