Meet ConceptCore

Our core product ConceptCore is an end-to-end metadata solution tailored to publishers. It was built around our Auto-tagging engine and is used by news publishers around the world.

Dive into ConceptCore & Auto-tagging

You can use the buttons below to quickly jump to the section you are the most interested in.

What is metadata and why is it important?
Why shouldn't journalists add it themselves?
What kind of metadata are we talking about?
How do we get it into our system?
Why pick iMatrics?
How does the Auto-tagging work?
Do you support any taxonomies or standards?
What are the technical details?

What is metadata and why is it important?

Metadata is data about data

Quality metadata can be used for a multitude of purposes. Look at the use cases below and see if you agree with the statement that Quality Metadata is essential.

Use cases to underline the importance of metadata

Why shouldn’t writers add metadata themselves?

It's not their focus. Writing quality content is.

There are two simple answers to this question. The first is that they don’t want to. The second is that since they don’t want to, there are challenges getting it done. Mistakes and inconsistencies are simply a part of reality when you have multiple people tagging their own content.

Our automatic solution is quick, consistent and precise which in turn leads to much higher quality of metadata.   

Save up to 7 min/article. For many organizations, this alone is reason enough.

What kind of metadata are we talking about?


Categories are high-level subjects with a specific purpose. This purpose could be to hold up the main site navigation or simplified content/production/interest analysis. Usually, we recommend 1 – 2 categories per article and that they should indicate the main aspect(s) of an article. The category part of the taxonomy usually isn’t changed very often.

Also, it is possible to integrate standards such as IPTC Media Topics or IAB Content Taxonomy as part of this.


Topics are more in-depth and detailed. Maybe you want to have a topic called Tea, for all your Tea interested users. Tea can then be activated as a followable tag and/or a Topic Page.

Generally topics can be used for detailed site navigation/automation, SEO including topic/theme pages, personalization functionality such as follow and get push notifications or personal news feeds and detailed user interest analysis.


Entities are named items of any of five subtypes. These subtypes are Person, Place, Organization, Event and Object. We usually have a natural understanding of Person, Place and Organization, but Event and Object may raise some questions. An Event is something that happens that is limited by time, such as the Summer Olympics 2016. An example Object could be a book or a movie. The use cases of entities are similar to that of topics.

P.S. We continuously update entities via our Wikidata Live Update service. You can also add your own or edit any of our suggested entities to suit your needs.

How do we get it into our system?

We are experienced with both building integrations and helping our customers/partners with theirs.

Currently there are available integrations to;

  • Naviga - Writer
  • Livingdocs
  • WoodWing - Aurora
  • Sourcefabric - Superdesk
  • Norkon - Live Center
  • WordPress
  • Aptoma - DrPublish

If you are not using any of the systems above, we have the information you need to integrate our solutions yourself or with our help.

Why pick iMatrics?

Tailored For You
  • We know each customer is unique – that's why we offer custom models build on your data.
  • Flexibility is important. Either through your own input, or via industry standards, we help you customize the taxonomy to your needs.
  • Via intuitive GUI tools, or API calls, you can control your data and easily tune the solution on your end.
Infinitely Scalable

  • Updates are performed without any downtime.
  • Our architecture is built to handle upscaling and downscaling seamlessly using proven tools on AWS.
Innovation Partner

  • Our premium support will guide you on your journey.
  • We are available for innovative projects to help you take your systems and sites to the next level.
  • Become a part of iMatrics Metadata & Media Innovation hub, where we showcase the latest technology and use-cases.
  • We arrange events to exchange experiences and find inspiration. This opens you up to our network of AI and metadata enthusiasts within the publishing space.

How does the Auto-tagging work?

The technical term for programs that analyze text is natural language processing, and there are thousands of engineers and researchers working in this field. That means there are fantastic resources to leverage. Our system uses a mix of state-of-the-art frameworks, traditional rule-based business intelligence, and our own proprietary AI methods. We combine these powerful methods with comprehensive databases based on open data such as OpenStreetMap and Wikidata to achieve the best result possible.

In short, we cherry-pick the best solutions to your specific problem.

Do you support any taxonomy standards?

On top of our own iMatrics News Taxonomy, we support IPTC Media Topics, IAB Content Taxonomy and use Wikidata IDs as a type of entity taxonomy. We also use OpenStreetMap for geodata. If you want us to add a new standard, just reach out!

iMatrics logo

What are the technical details?

ConceptCore consists of the following pieces;

  • The Auto-tagging engine.
  • The taxonomy database and our entity database, EntityDB.
  • Wikidata Live Update, which is our live entity synchronization feature.
  • Our administration suite, including the Concept Management tool, the Concept Suggestions inbox and the Tag Quality Assurance tool (aka Tagging Queue).
  • CMS integrations.
  • Education material.

There is also the Gender Balance Tool add-on with its Slack integration for feedback purposes.

Auto-tagging engine

The Auto-tagging engine lies at the center of the ConceptCore solution. It is built around our own proprietary, unsupervised and language independent classification algorithm. This algorithm in turn is based on our founder Berkant Savas' research in applied mathematics.


Our entity database which we commonly refer to as EntityDB is based on data from Wikidata, Wikipedia and OpenStreetMap. It is not just a collection of all the data from these three sources, but rather the results of an extensive ETL (Extract, Transform, and Load) process. We extract and combine the data, filter it extensively based on quality and overall usefulness to our customers, transform it into our data formats and load it into Elasticsearch/OpenSearch databases. Furthermore, this is not just a static script. We actively maintain and improve it based on customer needs, just like all our software.