Digital Asset Review Summarization With Fake Review Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Online reviews often contain ingenuine content, making it difficult for online stores to effectively organize and summarize reviews accurately, as users may be incentivized to leave hurried or irrelevant feedback, leading to a lack of genuine sentiment capture.
Innovation Solution
Implement a method using machine learning models to filter and summarize online reviews by identifying safety metrics, sentiment, and informativeness, generating a summary for digital assets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If online reviews are collected from multiple sources, then the quantity of reviews increases, but the quality and authenticity of reviews deteriorates due to inclusion of ingenuine reviews
Solution Approach 1:
The patent extracts and removes ingenuine reviews from the review set by identifying characteristics of fake reviews (gibberish text, irrelevant content, rushed submissions) and filtering them out, thereby maintaining the quantity of genuine reviews while improving overall authenticity
Solution Approach 2:
The patent introduces an intermediary processing system that analyzes reviews using multiple criteria (language models, sentiment analysis, informativeness metrics) to determine authenticity, acting as a mediator between raw review data and the final review display
2Measurement precision
If machine learning models are used to analyze each review, then the accuracy of sentiment analysis improves, but the computational complexity and processing time increases
Solution Approach 1:
The patent segments the review analysis process into multiple independent components: language detection, safety metric evaluation, sentiment analysis, and informativeness assessment, allowing each to be processed separately and efficiently
Solution Approach 2:
The patent applies partial analysis by focusing on key indicators (safety metrics, sentiment, informativeness) rather than analyzing every aspect of each review in depth, achieving sufficient accuracy without excessive computational overhead
Data Source
Figure 1
Figure 2
Figure 3
AI summary
One embodiment sets forth a method for managing information for digital assets. According to some embodiments, the method can be implemented by a computing device, and includes the steps of (1) receiving a plurality of reviews associated with a digital asset, (2) for each review of the plurality of reviews: (i) identifying, based at least in part on a language of the review, at least one respective machine learning model, (ii) retaining the review within, or removing the review from, the plurality of reviews based at least in part on a respective safety metric output by the at least one respective machine learning model in response to receiving the review as input, and (iii) when the review is retained within the plurality of reviews: establishing, for the review using the at least one respective machine learning model, respective sentiment and informativeness metrics, (3) generating a summary for the digital asset based at least in part on the sentiment and informativeness metrics, and (4) causing the summary to be displayed within a user interface associated with the digital asset.