Dynamic Interpersonal Relationship Modeling from Social Media
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing social media analytics fail to effectively model and visualize dynamic interpersonal relationships, particularly in distinguishing between different relationship types such as operational, personal, and strategic, and predicting their future strength over time.
Innovation Solution
A method and system that determine relationship types using a relationship model, perform timeline-based relationship strength segmentation with Group Lasso, and predict future relationship strength using the Extended Kalman Filter, while providing interactive visual analytics for monitoring relationship states through a visual interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If social media analytics are used to model interpersonal relationships, then relationship insights can be obtained, but the ability to distinguish between different relationship types and predict future strength is insufficient
Solution Approach 1:
The patent segments relationships into distinct types (operational, personal, strategic) using a relationship model that classifies interactions based on multiple attributes. This segmentation allows the system to differentiate between relationship categories while measuring their respective strengths, resolving the contradiction by creating structured categories that preserve information while enabling precise measurement.
Solution Approach 2:
The patent adds a temporal dimension to relationship analysis by implementing timeline-based segmentation that tracks relationship strength evolution over time. This dimensional expansion transforms static relationship data into dynamic trajectories, enabling both precise measurement at any point and preservation of historical relationship patterns that distinguish different relationship types.
2Loss of time
If relationship strength segmentation is performed, then past and current relationship strengths can be analyzed, but future relationship strength prediction capability is limited
Solution Approach 1:
The patent applies preliminary action by using Extended Kalman Filter to predict future relationship strength based on historical patterns. The system proactively estimates future states before they occur, allowing users to anticipate relationship evolution. This predictive capability compensates for the loss of future information while maintaining reliability through mathematical modeling of relationship dynamics.
Solution Approach 2:
The patent implements feedback mechanisms where predicted future relationship strengths are continuously refined based on actual observed data. The system compares predictions with real outcomes and adjusts its models accordingly, creating a closed-loop system that improves prediction reliability over time while maintaining comprehensive temporal analysis.
3Loss of information
If comprehensive relationship modeling is implemented, then relationship insights are provided, but the complexity of the system increases
Solution Approach 1:
The patent reduces system complexity by segmenting the relationship modeling into distinct modular components: relationship type classification module, timeline-based segmentation module, and prediction module. Each module handles specific aspects of relationship analysis independently, making the overall complex system manageable through functional decomposition while still capturing comprehensive relationship details.
Solution Approach 2:
The patent creates a universal relationship model that handles multiple relationship types (operational, personal, strategic) and multiple temporal analyses (past, present, future predictions) through a single integrated framework. This multi-functional approach reduces complexity by avoiding separate specialized systems for each relationship aspect, instead using one versatile model that adapts to different relationship scenarios.
Data Source
AI summary
Embodiments relate to relationship modeling and visualization from social media. One aspect includes determining a relationship type of a network-based relationship, between an individual and a network contact of the individual, from at least one social media data source. The relationship type is determined using a relationship model based on relationship types that include operational, personal, and business. Another aspect includes performing timeline based relationship strength segmentation using Group Lasso. The timeline based relationship strength segmentation specifies a past and current strength of the relationship. A further aspect includes predicting a future strength of the relationship using Extended Kalman Filter, and providing, through a visual interface, interactive visual analytics to view and monitor relationship states including the past, current, and future strengths over time.