Link analysis is the process of building a network of interconnected objects through relationships to discover patterns and trends. The main objective is to find and link information from various sources and to adequately represent and estimate the relevance of this information to discover hidden relationships. Link analysis is an iterative process, involving both automatic and manual steps depending on the data being analyzed. Link analysis and visualizations with link charts are key tools in building an understanding of how networks are structured and function. This understanding allows decisions to be made and actions to be taken that lead to the optimization, influence, or disruption of the network.
A link chart is a visualization of the relationships between different entities. Link charts can have many types of nodes (for example, person, building, or device), often labeled and symbolized by type. The links between the nodes are shown as a series of annotated lines. Entities are often either intrinsically mobile (people, vehicles, and cellular devices) or intangible (bank accounts and companies), with spatial and temporal properties that place an individual or group at a specific place during a specific time. The data is compiled from disparate sources, such as sightings, known meetings, credit card transactions, phone usage, movement data, home address, or place of business.
The link chart displays a large amount of entity data so you can visualize how a group of entities is organized, and how those entities are related to each other. Analysts use link analysis to analyze large amounts of data and to create a quality presentation showing a more accurate portrayal of entities and their relationships. A link chart can then be used to identify patterns between the nodes using graph analysis, including the following:
- Path analysis includes finding the shortest path or all the paths between the nodes.
- Centrality finds and highlights the nodes that are the most connected.
- Neighborhood detects all the nodes that are in the defined neighborhood and which neighbors are shared between two nodes.
Link, spatial, and temporal analysis integration
Link analysis deals with people, organizations, places, events, relationships, and other intangible connections between entities. Many data elements used in link analysis have quantifiable spatial properties, such as a person's residence or a meeting's location. Link analysis is enhanced by combining this analysis with spatial and temporal analysis. Integrating spatial, temporal, and link analysis processes and visualizations improves the quality of analyses as well as the effectiveness of the output. Using spatial, temporal, and link analysis side by side in the same workflow, a more comprehensive analytical process can be accomplished than by using one alone.
ArcGIS allows the visualization of entities and relationships in a link chart to be extended by incorporating the dimensions of space and time, enabling the influence and impacts of terrain and events to be considered when analyzing a network. Detailed and objective analysis can be conducted that enables a measure to be placed on how an individual node or an entire network is influenced by spatial and temporal factors. The many types of analysis include the following:
- The correlation of different sets of data between an individual's movements and incidents of a certain type
- The understanding of patterns of behavior in space and time, such as identifying patterns of life or likely points of interdiction
- Identifying hidden relationships between two or more items
- The degree to which the distribution of illicit substances or materials correlates with the demographics of an area
- The potential for a vehicle or pedestrian to cross a terrain, including how far it might be expected to travel in a given time frame
- The proximity of infected individuals to hot spots of disease outbreak
These types of analysis, and many more, can be applied to provide shared situational awareness, inform decision-making, estimate adversarial behavior, or focus collection efforts.
Much of the entity data in a link chart includes some form of spatial and time components, such as the following:
- Home or work address
- Meeting locations and time
- Places of interest
- Event or incident locations and times
These attributes form complex patterns that cannot be readily visualized without link analysis. ArcGIS provides the ability to bring these spatial and temporal attributes together, so you can see how they relate to each other in ways that are otherwise invisible. Using these attributes, a variety of spatial processing and analysis can be performed on the connected data, presenting the results of the analysis in a form that is easily understood.