What is a Knowledge Graph?
A knowledge graph is a structure used to represent our knowledge about the world in terms of entities (called nodes) and the relationships (called edges) between them.
A Node object consists of its type and its static and dynamic attributes. Static attributes are key-value pairs that belong to the node itself and they follow a fixed, well-defined schema based on the node's type. In contrast, dynamic attributes are described by edges between the nodes which can represent any type of a relationship between them. An example of a simple knowledge graph is available in Figure 1.
Figure 1: Example of a knowledge graph with nodes of type Person in yellow, and other nodes in dark grey. Edges between the nodes describe their dynamic attributes (such as place_of_birth or sex_or_gender).
In our knowledge graph, we also compute the relevance of each node. That information can be used for finding important nodes in the graph. There are two types of node relevances: absolute and relative. Absolute relevance indicates how important the node is across the whole knowledge graph. On the other hand, relative relevance describes how important the node is with respect to another node.To compute global node relevance, we use the PageRank algorithm whose score.
What Knowledge is linked in the Deep Explorer?
We want to make research faster and more efficient for media professionals. One of the key ways we do this is by constantly updating open source databases and adding relevant information to our standard knowledge graph provided by the Deep Explorer. Currently, the Deep Explorer focuses on knowledge based mainly on person nodes, such as actors and actresses, politicians, athletes or other celebrities.
While open source databases may not provide fully validated journalistic sources, they can be incredibly useful in pointing researchers in the right direction. Every piece of information from these databases includes a link to the original source, allowing users to follow up and verify the data themselves.
Can I add my own database to the Knowledge Graph?
In addition, it is possible to bring your own structured databases into the Deep Explorer, such as personnel records from media organisations or validated databases from trusted vendors. This is currently only possible via our staff and can't be done by the user.
Own databases can ensure that only verified information is included in the research process, adding an extra layer of reliability, and are used by ProSieben.Sat1 in their newsroom, who also worked with us on this European Union Stadiem research project.
By combining open source data with validated databases, the Knowledge Graph provides a maximum of knowledge and becomes a powerful research tool that helps users save time while maintaining a high standard of accuracy.
Note:
If you would like to include your own database in the Knowledge Graph, please contact our sales team for clarification and further details.