Social Capture Rules for Moderation Efficiency

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current social analysis tools capture a large number of social mentions from social networks, but only a small subset requires moderation, leading to inefficient moderation processes due to overly broad capture rules.

Innovation Solution

Analyzing social mentions using initial rule sets to identify commonalities in text and metadata, generating a new rule set with criteria that selects for more relevant social mentions, thereby reducing the number of mentions that need to be reviewed by moderators.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If initial capture rules are used to capture social mentions, then a large number of social mentions are captured, but the number of social mentions requiring moderation is small, leading to inefficient moderation processes

Engineering Contradiction:

Improvenumber of social mentions capturedVSAvoidmoderation efficiency

Core Design Contradiction:

Quantity of substanceVSProductivity

Solution Approach 1:

The patent extracts only the relevant social mentions that require moderation by analyzing captured mentions against historical moderation data and identifying patterns. This separates the useful subset (mentions needing moderation) from the larger captured set, improving moderation efficiency by focusing resources on relevant content only.

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs preliminary analysis of captured social mentions by comparing them against historical moderation data and identified patterns before presenting them for actual moderation. This preliminary filtering action occurs in advance, reducing the workload for moderators and improving overall process efficiency.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If capture rules are modified to reduce the number of captured social mentions, then moderation workload decreases, but accuracy in capturing relevant social mentions may be compromised

Engineering Contradiction:

Improvemoderation workloadVSAvoidaccuracy of capturing relevant social mentions

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system uses feedback from historical moderation data and actual moderation actions to continuously refine and update capture rules. By analyzing patterns in previously moderated content, the system learns which mentions are relevant and adjusts rules accordingly, maintaining high accuracy while reducing workload.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent dynamically adjusts parameters of capture rules based on analyzed patterns from historical data. By changing thresholds, keywords, and criteria based on learned patterns, the system optimizes the balance between capturing relevant mentions and reducing overall workload, maintaining precision while improving productivity.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS10120932B2Social capture rules

Publication Date: 2018.11.06 ADOBE INC

AI summary

The collection of social data from social networking services for moderation purposes is improved by analyzing social mentions captured using an initial set of capture rules. The text and/or metadata of social mentions previously captured using an initial rule set of capture rules may be analyzed to identify common text and/or common metadata amongst those social mentions. A new rule set may be generated with capture rules having criteria selected based on the identified common text and/or common metadata. The new rule set may then be applied to capture new social data.