Sentiment-Based Document Sorting in Online Communities
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Online community interfaces primarily display documents based on timing or frequency, leading to prominence of emotionally charged posts over more informative ones, which may not accurately reflect the author's analysis and can misrepresent the topic to clients.
Innovation Solution
A method to sort and display documents in an online community based on sentiment level by calculating sentiment scores using predefined rules for language elements, assigning priority values, and applying tiebreak techniques to differentiate documents with equal scores, ensuring that less emotional content is displayed more prominently.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If documents are sorted and displayed based on timing or frequency, then recent or frequent posts are prominently displayed, but emotionally charged posts may unduly influence the viewpoint and less informative posts may be displayed less prominently
Solution Approach 1:
The patent changes the sorting parameter from timing/frequency to sentiment level. By calculating sentiment scores for each document and using these scores as the primary sorting criterion, the system reorganizes document prominence based on emotional content rather than temporal or frequency metrics. This resolves the contradiction by ensuring that documents with lower sentiment scores (more informative, less emotional) are displayed more prominently, while still maintaining ease of operation through automated sentiment-based sorting.
2Quantity of substance
If posts with high sentiment language are displayed prominently, then emotional posts gain visibility, but the ability of clients to interpret and evaluate the topic accurately is inhibited
Solution Approach 1:
The patent inverts the traditional approach by displaying posts with lower sentiment scores more prominently rather than those with higher sentiment. The sentiment score calculation identifies emotionally charged language, and the sorting mechanism deliberately prioritizes posts with lower scores. This inversion ensures that more informative, less emotional posts gain visibility, thereby improving topic interpretation accuracy while maintaining adequate post visibility through the inverted ranking system.
3Loss of information
If documents are sorted by sentiment level, then informative content is prioritized, but the system complexity increases due to sentiment analysis requirements
Solution Approach 1:
The patent implements self-service by enabling the system to automatically calculate sentiment scores and sort documents without requiring manual intervention. The sentiment analysis component autonomously processes each document, assigns a sentiment score, and the sorting mechanism automatically reorganizes documents based on these scores. This automation reduces the need for complex manual curation systems while maintaining accurate content representation, effectively managing system complexity through self-service processing.
Data Source
AI summary
An approach is described for sorting and displaying documents according to sentiment level in an online community. An associated system may include a processor and a memory storing an application program, which, when executed on the processor, performs an operation that may include selecting a review topic in an online community and identifying a plurality of documents contributed for the review topic. The plurality of documents may include at least one of a product review submission, a marketing survey submission, a social network activity stream post, a discussion forum post, a weblog post, and an audiovisual sample. The operation further may include obtaining sentiment data associated with each of the plurality of documents developing a sentiment model based on the obtained sentiment data. Additionally, the operation may include organizing and presenting the plurality of documents in an online community interface based on the sentiment model.