Social Identity Clustering via Iterative Graph Merging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Identifying all social accounts belonging to a user from publicly available and unverified social data is challenging due to the proliferation of online social sites and varying user account listings.
Innovation Solution
A method involving the creation of a connection graph from public social data, clustering identities based on 'me' edges, and iteratively merging nodes with strong connections to form clusters, which helps in verifying and aggregating user identities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If public social data is collected from multiple social sites, then the quantity of social identity information increases, but the reliability of identifying user identities deteriorates due to unverified data
Solution Approach 1:
The system uses feedback loops where clustering results are continuously refined by re-evaluating connection graphs. The iterative clustering process provides feedback on identity groupings, allowing the system to adjust and improve reliability by reinforcing consistent patterns across multiple social sites while filtering out inconsistent or erroneous connections.
Solution Approach 2:
The patent introduces an intermediary clustering mechanism that acts as a mediator between raw public social data and final identity identification. The connection graph and clustering algorithm serve as intermediaries that process, verify, and validate relationships between social identities, transforming unverified public data into reliable identity groupings through structured analysis.
2Measurement precision
If clustering algorithms are applied to identify user identities, then the accuracy of identity aggregation improves, but the computational complexity increases
Solution Approach 1:
The patent segments the identity identification process into distinct phases: constructing connection graphs from public data, applying clustering algorithms to group identities, and validating results. This segmentation allows the system to manage computational complexity by processing data in manageable stages rather than attempting simultaneous analysis of all social identity relationships.
Solution Approach 2:
The system performs preliminary actions by pre-processing public social data into structured connection graphs before applying clustering algorithms. This preliminary organization of data into graphs with defined nodes and edges reduces the computational burden during the actual clustering phase, as the data is already structured and ready for analysis.
3Reliability
If users provide explicit social identity information, then the verification of identities improves, but the completeness of identity collection deteriorates as users may not provide all their accounts
Solution Approach 1:
The patent merges multiple data sources by combining explicitly provided user identity information with publicly available social data from multiple sites. The connection graph integrates both verified user-provided connections and publicly observable relationships, allowing the system to compensate for incomplete user disclosures while maintaining reliability through cross-validation of multiple data sources.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for social identity clustering. In one aspect, a method includes receiving a connection graph representing public social data, where the nodes represent social identities and each edge is either a “me” edge between identities claimed to belong to the same person or a “friend” edge between identities claimed to belong to different identities. The method further includes converting the graph to a cluster graph in which each node initially corresponds to a single node of the connection graph. The method further includes updating the cluster graph by iteratively merging cluster nodes based on an analysis of the weight of the “me” edges connecting them, and then replacing the merged cluster nodes within the graph with a new cluster node containing the merged cluster nodes, where the edges of the new cluster node are the aggregated edges of the merged cluster nodes.