Comment Ranking by Search Engine Using Quality Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in quickly and efficiently retrieving helpful comments from a large number of user-generated comments on e-commerce platforms, as conventional ranking methods prioritize recent comments over valuable information, and are often overwhelmed by spam and irrelevant content, leading to impatience and abandonment of browsing sessions.
Innovation Solution
A method and apparatus for comment ranking by a search engine that extracts terms describing a target object, determines useful attributes, calculates scoring indexes based on the number of useful attributes, readability, and useless attributes, and ranks comments accordingly to prioritize high-quality information, allowing users to quickly find relevant information and improving browsing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If comments are ranked by publishing time (most recent first), then users can see the latest feedback, but users cannot quickly find high-quality helpful content and must browse through many pages
Solution Approach 1:
The patent changes the ranking parameter from simple publishing time to a composite quality score that includes multiple dimensions: usefulness score (based on helpful votes), spam score (detecting advertising and irrelevant content), and recency weight. This multi-parameter approach resolves the contradiction by prioritizing high-quality comments while still considering timeliness, allowing users to quickly find helpful information without manually browsing through pages of chronological comments.
2Quantity of substance
If all user-generated comments are displayed, then comprehensive feedback is provided, but spam and irrelevant content overwhelm useful information
Solution Approach 1:
The patent extracts and removes harmful elements (spam and irrelevant content) from the comment set through automated detection algorithms. The system identifies spam based on patterns such as excessive keywords, advertising language, and irrelevant topics, then either filters these comments out or assigns them negative scores that prevent them from appearing in ranked results. This allows the system to maintain comprehensive feedback while eliminating harmful content that would otherwise overwhelm useful information.
Solution Approach 2:
The patent converts the presence of spam comments into a benefit by using them as training data for improving the detection algorithm. The system learns from spam patterns and becomes more effective at identifying and filtering harmful content over time. Additionally, the spam detection mechanism itself becomes a useful feature that users can trust to curate quality content automatically.
3Loss of information
If users manually browse through pages of comments, then they can read all feedback, but user patience decreases and browsing sessions are abandoned
Solution Approach 1:
The patent performs preliminary sorting and filtering of comments before they are presented to users. The system pre-calculates quality scores, detects spam, and ranks comments in advance, so that when users view the comment section, they immediately see the most helpful and relevant content at the top. This preliminary processing eliminates the need for users to manually browse through pages, as the information is already organized in an easily consumable format that maintains both comprehensiveness and user experience.
Data Source
AI summary
The present disclosure provides example methods and apparatuses for implementing comment ranking by a search engine. One or more terms describing a target object are extracted from a comment in connection with the target object. One or more useful attributes included in the comment are obtained according to the terms describing the target object. An scoring index the comment is determined according to a number of the useful attributes. The comment is scored according to the index. The comment is ranked according to the score. The present techniques enable a user to quickly and efficiently view helpful comments and help the user make an informed decision.