Filling in the Crime Intelligence Gaps with Entity Extraction

Law enforcement agencies like the FBI receive high volumes of critical information in the form of unstructured data. This unstructured data comes both from internal sources such as crime reports, case narratives, and interviews, and from the general public through tip lines.  Online news and social media posts may also contain information critical to a case.

The challenge is that manually reviewing unstructured data takes time and resources, which are especially precious in the context of resource-strapped law enforcement agencies and time-sensitive criminal investigations. Imagine trying to read all of this unstructured data during an emergency situation or a developing criminal event such as a terror attack, mass shooting, hostage crisis, child kidnapping, serial rapist, arson campaign, etc.

Entity Extraction for Crime Intelligence

Advanced text analytics technologies like Entity Extraction can expedite the processing and review of unstructured data and free up agents to do more complex analytical work. It can also facilitate the discovery and connection of critical information from seemingly unrelated data sets and enable alerts.

Entity Extraction can be used to identify key concepts such as names, phone numbers, vehicle descriptions, license plates, people descriptions, place names, addresses, as well as events such as killings or kidnappings and relationships between entities such as kinship, associates, and affiliations. Once these concepts have been identified and associated with the original documents as metadata, the information becomes available not only to search but can also be discovered through advanced analytical tools such as semantic indexing, link analysis, and geospatial analysis.  The ultimate goal is the identification of suspects, perpetrators, networks, operatives, and criminal activity patterns.

Why Use NetOwl’s Entity Extraction

There are a number of ways in which NetOwl offers unique Entity Extraction capabilities critical for Crime Intelligence:

1. NetOwl identifies an extensive ontology of named entities with state-of-the-art accuracy, including names of people, organizations, places, facilities, phone numbers, license plates, vehicles, addresses, etc.
2. NetOwl offers a unique and advanced capability to identify a broad range of relationships (e.g., person-associate, person-affiliation) and events (e.g., attacks, travels, transactions), and their participants out of the box. These relationship and event extraction capabilities allow for a far more advanced analysis beyond the simple links afforded by co-occurrence. NetOwl enables a deeper analysis of documents such as network link analysis to reveal clues critical to a given criminal investigation.
3. NetOwl offers name normalization so that names can be more easily resolved and aggregated across documents to support semantic search, faceted search, and advanced analysis (e.g., timelines, charts).
4. NetOwl offers semantic disambiguation of place names (e.g., Springfield, VA vs. Springfield, MA) and smart geotagging not only of place names but also of other entities (e.g., people, organizations), thus enabling a geographic view of criminal activity for geospatial analysis. In addition, NetOwl outputs a confidence score for the geotagged locations and geotags relative location phrases (e.g., “30 miles northwest of Springfield”)
5. NetOwl is engineered specifically for high-volume processing of multiple different data sources, which is critical in investigations where time is of essence. Additionally, NetOwl integrates document converters to handle hundreds of native document formats.
6. NetOwl integrates easily with databases, document and content management systems, portals, and other sources of electronic content.  Its REST API supports easy integration into existing workflows.  NetOwl can be deployed on premise or in the cloud for horizontal scalability, offering rapid processing of massive amounts of data.

In summary, NetOwl offers an extensive set of Entity Extraction capabilities to turn unstructured data into actionable insights that fill in crime intelligence gaps.