Textual Feedback Mining Using Lexical Patterns and LDA
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods fail to efficiently extract actionable information from textual feedback, such as suggestions and defect reports, from users of applications, products, and services, making it difficult for businesses to improve customer satisfaction and identify issues effectively.
Innovation Solution
The method involves mining textual feedback using lexical/Part-of-Speech patterns, distant supervision-learning techniques, and Latent Dirichlet Allocation to identify and summarize suggestions and defect reports, enabling the extraction of actionable insights from user feedback.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional manual analysis methods are used to extract information from textual feedback, then the accuracy of extracting actionable information is improved, but the time consumption and labor requirements increase significantly
Solution Approach 1:
The patent replaces manual mechanical analysis with automated computational methods including NLP algorithms, machine learning models, and pattern recognition systems that automatically process and extract actionable information from textual feedback, eliminating the need for human analysts to manually review each feedback item
Solution Approach 2:
The system enables self-service automated extraction where the feedback analysis system independently processes textual feedback, identifies patterns, extracts actionable information, and generates insights without requiring continuous human intervention or manual curation of the analysis process
2Quantity of substance
If comprehensive feedback analysis is performed to identify all possible suggestions and defects, then the completeness of extracted information is improved, but the processing complexity and computational resources required increase
Solution Approach 1:
The patent segments the feedback analysis process into distinct functional modules including text preprocessing, pattern matching, machine learning classification, information extraction, and summary generation. Each module handles a specific aspect of the analysis, making the overall complex task manageable and scalable through modular architecture
Solution Approach 2:
The system employs selective analysis techniques that focus computational resources on the most promising feedback items and patterns, using machine learning models to prioritize analysis of feedback that is most likely to contain actionable information, rather than uniformly processing all feedback with equal intensity
Data Source
AI summary
Methods, systems, and apparatus for accessing a set of feedback items, identifying a candidate feedback item from the set of feedback items using a lexical pattern, generating a gist phrase that summarizes the candidate feedback item, and causing display of a user interface on a client device, the user interface including the gist phrase.