semantics of conflicting and suspicious information
In today's environment with avalanche of information, intelligence requires a capability to detect and resolve conflicting, inconsistent, suspicious, and deceptive data, reducing the uncertainty in analysis associated with misinformation. This need spans both the military and intelligence domain fighting global networks of loosely connected cells that employ centralized decision making with decentralized execution of operations, and the commercial domain where insight into new products drives both investment and strategic planning purposes.
semSCI, a Semantic Application to Detect and Resolve Suspicious and Conflicting Information, combines diverse sources of structured and semi-structured information within a common schema to automatically tag entities and relationships, including metadata about provenance such as timeliness and reliability. semSCI represents the asserted facts in the structured and semi-structured information using a semantic annotation formalism to create a knowledge graph data model. Leveraging this knowledge graph, semSCI can infer not only spatial, temporal, and naming conflicts but any inconsistency indicating suspicious and deceptive information involving the logical expressions of subject and property values in the multi-dimensional semantic space with the use of stream entropy algorithms.
Conflicting vs. inconsistent vs. Suspicious vs. Deceptive:
• semSCI models the semantics of conflicting (e.g identity based) and inconsistent (e.g. organizational affiliations), suspicious (e.g. changes in operational tactics) and. deceptive (e.g product dissimulation and simulation) information using Descriptive Logic
Logical vs. Probabilistic Anomalies:
• semSCI automatically detects both logical and probabilistic anomalies in an integrated manner
Hard vs. Soft Inconsistencies:
• Semantics drives the detection of hard inconsistencies while entropy drives the detection of soft inconsistencies.
• semSCI uses entropy to measure the level of conflict and inconsistency, and detect suspicious and deceptive information
• semSCI computes the entropy of a stream of information, and a measure of change in entropy using the Kullback-Leibler Divergence
REQUEST semsci DEMO
• Automates gathering and analyzing intelligence about the performance of a product being designed
• Filters streams of information to flag conflicting and inconsistent information for knowledge management, and suspicious and deceptive information for analyst interpretation
• Sifts through the avalanche of information generated around the drug approvals during clinical trials
• Analyzes market information about competitor product strategy, market development, and sales strategy
• Analyzes cyber security incident reporting to assess attribution of actors