Summarization Engine for Decomposing User Comment Ratings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users of websites face difficulties in comprehending large numbers of short comments with overall ratings, as these ratings do not provide specific insights into various aspects of a target entity, leading to inadequate information for decision-making.
Innovation Solution
A summarization engine that decomposes overall ratings into rated aspect summaries by identifying major aspects, predicting ratings for each aspect, and extracting representative phrases to provide detailed insights into specific aspects of a target entity, such as shipping, communication, and service.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If overall ratings are provided for comments, then users can quickly see rating information, but users cannot gain specific insights into various aspects of the target entity
Solution Approach 1:
The patent segments the overall rating into multiple aspect-specific ratings by identifying and extracting key aspects from comments. The summarization engine divides the comment data into distinct aspects (e.g., product quality, shipping, customer service) and provides separate rating summaries for each aspect, allowing users to obtain both overall and specific insights without additional effort.
2Quantity of substance
If many user-generated comments are received, then more information is available about the target entity, but the number of comments becomes unmanageable and difficult to comprehend
Solution Approach 1:
The patent extracts key information from the large volume of comments by identifying important aspects and generating representative phrases. The summarization engine extracts only the most relevant rating information and aspect summaries, filtering out redundant details while preserving essential insights. This extraction process reduces the manageable comment volume to a concise summary that maintains information quality.
Solution Approach 2:
The patent merges multiple individual comments into consolidated aspect summaries. By combining similar comments and ratings into unified aspect-specific summaries, the system reduces the number of discrete comment items while preserving the collective information. This merging process transforms hundreds or thousands of individual comments into a manageable set of aspect summaries with representative phrases.
3Loss of information
If overall ratings are provided, then rating information is available, but the ratings do not provide specific insights into various aspects for decision-making
Solution Approach 1:
The patent applies local quality by providing aspect-specific rating summaries that tailored information to different aspects of the target entity. Instead of a single overall rating, the system provides localized rating information for each aspect (e.g., product quality rating, shipping rating, customer service rating), allowing users to make informed decisions based on specific aspect performance rather than a generic overall rating.
Data Source
AI summary
A method and a system for summarization of short comments are provided. The system comprises a memory to store a plurality of comments. Each of the plurality of comments including an overall rating and at least one phrase. The system also includes one or more processors to implement an aspect module to identify a head term based on a portion of the plurality of comments and to map the portion of the plurality of comments to an aspect corresponding to an attribute of an entity. The one or more processor also implement an extraction module to extract, from the portion of the plurality of comments, a representative phrase corresponding to the aspect.