Social Media Knowledge Base for Near-Real-Time Event Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current event detection systems in social media are delayed and struggle to sift through vast amounts of noise to deliver timely and relevant information, such as news and business insights, with existing systems taking minutes to detect events and failing to efficiently filter out spam and advertisements.
Innovation Solution
A system and method for identifying, collecting, and presenting important and influential social media sources by retrieving account information, classifying accounts based on type, ranking them by influence, and storing and presenting relevant postings to users, utilizing a social media knowledge base system that includes an account mining module and a posting collection and presentation module.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If existing event detection systems monitor social media data streams, then they can detect events, but the detection latency is too long (minutes delay)
Solution Approach 1:
The patent segments the massive social media data stream into manageable portions by focusing on specific accounts and postings of high importance or influence. Instead of processing all 700 million tweets daily, the system identifies and monitors only relevant accounts, dividing the problem into smaller, more efficient processing units that reduce detection latency.
Solution Approach 2:
The system performs preliminary actions by pre-identifying and storing account information for important and influential social media accounts before event detection is needed. This advance preparation includes classifying accounts by type and ranking them by influence, so that when an event occurs, the system can immediately query pre-filtered data rather than searching through the entire data stream.
2Loss of information
If the system monitors the entire social media data stream, then it can capture all information, but the noise (spam, advertisements, chit-chat) overwhelms useful information
Solution Approach 1:
The patent applies local quality by treating different social media accounts differently based on their characteristics. Important and influential accounts receive prioritized attention and deeper analysis, while less relevant accounts are filtered out. This selective approach ensures that useful information from high-quality sources is captured while noise from low-quality sources is eliminated.
Solution Approach 2:
The system introduces an intermediary layer of account classification and ranking that mediates between the raw social media data stream and the final information delivery. This intermediary process filters and prioritizes accounts based on their importance and influence, acting as a buffer that separates useful information from noise before the data reaches the event detection system.
3Speed
If the system processes and analyzes all social media postings in real-time, then it can deliver timely information, but the computational complexity and resource requirements become unmanageable
Solution Approach 1:
The patent segments the processing task by dividing social media accounts into categories based on their type and influence ranking. This segmentation allows the system to process only the relevant segments (important and influential accounts) in real-time, while other segments are processed less frequently or filtered out, reducing overall computational complexity.
Solution Approach 2:
The system changes parameters by dynamically adjusting the importance and influence thresholds for account selection. By modifying these parameters, the system can optimize the balance between processing speed and information quality, delivering timely information while managing computational resources efficiently through adaptive parameter tuning.
Data Source
AI summary
A method of identifying and presenting accounts and postings of a social media system may include: retrieving, via at least one communication interface of the social media system, account information for a plurality of social media accounts; classifying, based on the retrieved account information, the plurality of social media accounts according to account type; ranking, based on the retrieved account information, the plurality of social media accounts according to perceived importance or influence; storing, in an account database, a representation of a subset of the plurality of social media accounts having a ranking greater than a predetermined threshold; retrieving, via the at least one API, postings of the stored social media accounts; and generating, for display on a user system, a user interface to present the retrieved social media postings for the stored accounts organized according to at least one of: account type, or ranking.