4 Things NOW Lets You Do With Content

News on the Web (NOW) is a free public service, showcasing the opportunities a dynamic semantic publishing platform opens up before media & publishing companies.

NOW lets you go beyond conventional publishing and get a real feel of the world where semantic technologies are already shaping the way we search, discover and consume content.

Dynamic semantic publishinghas the potential to improve content creation and consumption. With the help of semantic technologies readers are served the content they most need, and publishers are given the tools to manage content in an efficient, future-proof manner.

In this blog post you will find 4 things that a dynamic semantic publishing platform (what NOW is) lets you do with content.

1. Go beyond free flowing texts to take advantage of structured metadata

Searching for, presenting and grouping information is burdensome when done manually. NOW makes these processes easier, being able to automatically:

  • Aggregate content related to a specific concept
  • Recommend content
  • Serve

For example, when news about Samsung gets onto the platform, it automatically enters a number of various relationships, based on the recognized concepts, mentioned in the text.


Annotation suggesting that Samsung and Huawei are competitors.

These concepts can be further related to each other, depending on the reader’s information needs and interests.


We now know that Chung works as an analyst in Nomura. And what he said about the smartphone market.

The above described capabilities stem from a process, key to the platform, and that is the process of concept extraction (called also “semantic annotation”). This process is about identifying concrete concepts, named entities, numbers, datasets and similar objects. In plain English this means automated adding of additional information to a free flowing text thus making the content easy to reuse and repurpose.


The extracted concept itself is defined by a number of relationships.

Concept Extraction Benefits

The structured metadata, extracted from free flowing texts, enables you  to present and group information in a number of ways. The most trivial one is to highlight and hyperlink concepts.

On NOW you can also see topic pages  which aggregate content related to specific concepts and at the same time show recommended content based on semantic fingerprints (i.e. automatic enrichment of content with tags, concepts, relationships and topics).

2. Let the machines do the heavy-lifting of content collection

With NOW you can experience what dynamic semantic publishing has to offer in terms of content aggregation, collection, recommendation and extraction.

Explore NOW and you will be able to:

  • Follow how concepts trend in the news
  • Get recent articles about chosen concepts
  • See the concepts that usually co-occur with other concepts
  • Easily reach extracted information such as what people were quoted saying in the news.

NOW has around 150 000 topic pages with People, Locations and Organizations. These pages present concept descriptions, how concepts trend in the news, recent articles about the concepts, what concepts they usually co-occur with, as well as other extracted information such as what people were quoted saying in the news.


For example, the topic page on Vladimir Putin shows a lot about who he is, what his religion is, when he was born, who his parents are, and so on.

On this particular topic page, you can also see the recent news about him and at which points in time he peaked in the news.


The topic page contains a section of entities associated with one another.


This section lets you see the usual context in which Vladimir Putin is mentioned. As the picture shows, there are 323 news articles  on NOW that mention both Putin and the crisis in Ukraine. Angela Merkel is represented as an associated entity too. Her circle is smaller , as she was mentioned less frequently together with Putin.

All of these bubbles are clickable, so if somebody is interested in the topic page of the United Nations, they could easily find their way around

Content Aggregation Benefits

One of the greatest pluses of clustering content around various concepts is the rich navigation. The new, interrelated ways of navigating through content substantially betters the experience of content consumption for the end-user.

From a publisher’s point of view, content aggregation enables journalists to summarize, research and discover related facts, various statistics etc. with less effort, some space for creativity and critical thinking.

3. Filter relevant and recent content

A dynamic semantic publishing platform includes a recommendations engine, which can be used to serve relevant content and ads, either based solely on context, or on user behaviour, or on both.

On NOW, the contextual recommendation flavour of the engine is being shown, as there is no tracking of user behaviour (You can try the behavioural recommendations on Financial Times’ website). This version of NOW can:

  • Give recommendations for content
  • Serve relevant content

Consider the following example – an article about the slight increase of US consumer prices is matched with relevant articles using the most relevant terms. Thus, you get the following result:


The recommendations engine opens the door for the creation of custom content streams for each user, or dashboards, showing what the different trending topics are along with what’s happening with the things users are interested in.

Relevant and Recent Content Benefits

Serving relevant and recent content, results in two of the most wanted things for a publisher: a sticky website and content users.

In the examples below a user can find everything related to Serena Williams, following the generated links in the news for the tennis player, the associated sections on the aggregated Topic page for her and finally her recent quotes. All the related content is one or two clicks away.Generated-pages-for-an-entitiy-Serena-Williamns-1024x486Generated pages for an entity Serena Williams


Generated sections for the entity (in this case a person) are one click away


Gathered recent quotations by Serena Williams

4. Expand the opportunities you have when reaching content via search

The ability to perform complex searches that go beyond keywords is vital for efficient content creation and management. A dynamic semantic publishing platform lets you perform faceted, hybrid and complex searches.

With NOW you can perform:

  • Complex queries
  • Full text searches
  • Searches for a person’s opinion (not included in the current version of NOW)

For example, if you wonder what Albert Einstein, New Jersey and Neil Armstrong have in common, NOW has the answer. What they have in common is NIKE. Why?

Apparently, Nike was sponsoring an event where the two greats were honored.


Next, you can mix the faceted search query with a full-text search (FTS) query to find documents containing particular concepts and phrases.


Finally, you can do much more complex queries when there is rich metadata associated with the free text. For example, we can query  a person’s opinion about a particular topic within a given time range. There are no examples in NOW, however, as it is far from trivial to expose this functionality in a generic way. The potential for such searches is there though, they just require the implementation of custom (micro) services to do the job.

The Benefits of Faceted, Hybrid and Complex Searches

These types of searches allow users to access content not only via keywords but also via phrases, facets and full text search. Thus readers can easily get to the most important and relevant content which in turn improves substantially their experience.

Powerful searches are also invaluable when conducting journalistic fact drills or researching  into new, unknown relationships and insights.

What else you can do with NOW?

On an ever more interconnected web, readers want to be not only informed but also interested and intrigued. Relevant content is key to providing these experiences: interest and engagement are earned with relevancy and recency, and depth and breadth of information is what satiates readers’ needs best.

Some of the other publishing usages of NOW as a dynamic semantic publishing platform include:

  • An authoring tool which extracts the concepts from the currently written text and sends requests to get recommendations for similar materials as the author types.
  • A tagging tool which produces all the tags for an article (the most relevant) which are edited manually by exception (as opposed to what is the current widespread practice to tag everything manually, which usually results in inconsistent tagging).
  • A commercial service, which allows people to get content based only on their preference (for less than the one-subscription-read-all price).
  • A marketing service, which helps sell the above mentioned people more content they might like.
  • A tool which aggregates historical content on a set of topics and is used to create magazines or even textbooks.

A Brand New Land to be Explored

NOW is not a mere showcase of a technology, it is also a sneak peek into  the future of publishing where you need to create and curate content efficiently for better engagement

As online publishing is not just publishing the old way, but online. It is a brand new territory that is to be further explored and cultivated. The application of semantic technologies and the use of metadata gives you this chance.

Interested in the semantic technologies behind NOW and the technical details related to the features about which you’ve just read?

Stefan Enev, the Lead Technical Architect  of the Semantic Annotation & Search group at Ontotext, has the answers for you in an upcoming white paper. Stay tuned for the link.

Meanwhile, check out NOW, play with it and share your insights and ideas.

Tell us what you think and how we can improve in the comments below.

Teodora Petkova

Teodora Petkova

Teodora is a philologist fascinated by the metamorphoses of text on the Web. Curious about our networked lives, she explores how the Semantic Web vision unfolds, transforming the possibilities of the written word.
Teodora Petkova

Related Posts

  • Semantic Information Extraction and the New Digital Disorder

    Semantic Information Extraction: From Data Bits to Knowledge Bytes

    Semantic information extraction is a boring name for a fascinating task: pulling out meaningful data from textual sources. With its help, text chunks become data bits, data bits become semantic metadata and semantic metadata become knowledge bytes – data pieces, ready to be leveraged for insights, decisions and actions.

  • Revolution of Linked Open Data

    The Web as a CMS: How BBC joined Linked Open Data

    Editorial wants to create faultless content and it is hard for them to imagine that quality coming from anyone else but their team. The dilemma these days is how do you maintain that high-quality in an era of shrinking editorial budgets and ever increasing amounts of data. Early on the BBC decided not to mint their own IDs but to utilise existing URIs for musical artists from a freely available database MusicBrainz. BBC went further and made the strategic decision to also use its resources to help improve the MusicBrainz database.

  • S4 Logo

    Empowering Your Medical Content with the New Healthcare Tagger on the Self-Service Semantic Suite (S4)

    Healthcare Tagger is the Self-Service Semantic Suite’s (S4) new tool for text analysis of various types of medical documents. It makes information extraction of biomedical knowledge quicker and more precise, and ultimately enhances your semantic analysis of medical records.

Back to top