Social Network Event Prediction Using Multi-Layer Data Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems fail to effectively identify social relationships and users likely to show interest in future protest events based on past social media interactions, despite recent work on social network analysis and online interactions during protests.
Innovation Solution
A system utilizing network data for event prediction, which includes a multi-layer representation of social media posts and user relationships, filtering new posts to determine their relevance to potential future events, and providing a quality score for event prediction by comparing them against a social network and audit trail database.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If social network analysis is performed on past protest posts to identify influential users, then the ability to predict future protest events is improved, but the complexity of the system increases due to multi-layer database representation and network analysis requirements
Solution Approach 1:
The system segments the social network data into multiple layers: a post layer representing protest-related posts and a user layer representing users who interact with these posts. This segmentation allows the system to analyze network characteristics separately for posts and users while maintaining their relationships through inter-layer links, improving prediction accuracy without overwhelming complexity
Solution Approach 2:
The system transitions from analyzing single-dimensional post content to multi-dimensional analysis by creating a multi-layer network structure. The post layer and user layer add different dimensions of information (content vs. social relationships), enabling more accurate prediction of future protest events through comprehensive network analysis
2Measurement precision
If new social media posts are filtered and compared against social network database to provide quality scores, then the precision of event detection is improved, but the processing time and computational resources increase
Solution Approach 1:
The system performs preliminary actions by pre-processing and storing social network data in a structured multi-layer database format before prediction is needed. Audit trails are maintained and network relationships are established in advance, so when new posts need to be evaluated, the system can quickly compare them against pre-organized data rather than processing everything from scratch
Solution Approach 2:
The system replaces manual or simple automated filtering with an intelligent comparison mechanism that uses the multi-layer network structure and audit trails. This substitution enables automated quality scoring that considers social network relationships and historical patterns, improving detection precision while reducing the need for time-consuming manual analysis
Data Source
AI summary
Described is a system for event prediction on microblogs. In operation, the system receives a social media post stream from a social network to generate and maintain a social network database and an audit trail database. New social media posts are filtered to determine if the new social media posts are related to a possible future event. The new social media posts are compared against the social network database and audit trail database to provide a quality score, the quality score representing a likelihood that at least one of the new social media posts is a true prediction of a future event. If the quality score is determined to be true, the detection is published as a true prediction of a future event.