Semantic Analysis of Negative Review Sentiment for Product Recommendations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for providing product recommendations based on user-generated reviews face challenges such as selection bias, influence from providers, and difficulty in accounting for personal differences, making it hard to identify pertinent information from a large body of reviews.
Innovation Solution
A method that utilizes semantic analysis to identify negative sentiment key phrases from user-generated reviews, correlates them with product characteristics, calculates weights, and generates a report listing scored product characteristics for each product, allowing users to filter recommendations based on their interests.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If collaborative filtering is used to provide personalized recommendations, then recommendations can be tailored to user preferences, but the system becomes difficult to operate and requires complex feedback mechanisms
Solution Approach 1:
The patent extracts only the negative sentiment key phrases from the review data, separating them from the rest of the review content. This extraction allows the system to focus on identifying problematic product characteristics without being overwhelmed by the entire review corpus, thereby simplifying the operation while maintaining personalization capability through the extracted negative feedback patterns
2Loss of information
If all product reviews are analyzed to provide comprehensive recommendations, then more information is available, but the system becomes more complex and harder to navigate
Solution Approach 1:
The system extracts only the negative sentiment key phrases from the review data, separating them from the rest of the review content. This extraction allows the system to focus on identifying problematic product characteristics without being overwhelmed by the entire review corpus, thereby simplifying the operation while maintaining personalization capability through the extracted negative feedback patterns
Solution Approach 2:
The patent segments the review data by identifying and isolating negative sentiment key phrases as distinct entities. This segmentation allows the system to process and analyze only the relevant negative feedback portions, reducing the complexity of reviewing entire datasets while preserving the essential information needed for recommendations
3Reliability
If positive reviews are used to generate recommendations, then product strengths are highlighted, but selection bias and provider influence skew the recommendations
Solution Approach 1:
Instead of using positive reviews to generate recommendations, the patent inverts the approach by using negative sentiment key phrases from negative reviews. This inversion allows the system to identify product characteristics that consumers dislike and avoid, providing more reliable recommendations that are less susceptible to provider influence and selection bias, as negative feedback is less likely to be manipulated by providers
Data Source
AI summary
A product recommendation system and method identify product characteristics from customer reviews using a semantic analysis of the product review text. The semantic analysis identifies negative sentiment keywords associated with one or more product characteristics in the customer review and assigns each negative sentiment keyword a value. The value of each identified negative sentiment keywords is then used to calculate a score for the product characteristic to which the negative sentiment keyword is correlated. A product recommendation report comprising the identified products, their product characteristics, a list of scored product reviews, or a combination thereof is then presented to the end user.