Discover the “technology bricks” that power the CPN platform


Our new report outlines the conceptual architecture and the technological infrastructure – what we call “technology bricks” – that power the CPN platform. The full report includes a description of each component, the functionality it provides, along with parameters, inputs, output, and API examples.

These components include Semantic Lifting, Topic Extractor, Uplifting/Depressing Article Classifier, Recommender AB-Testing, and Twitter Analytics

The set of “technology bricks” took as a starting point the user requirements collected earlier in the project. These “bricks” constitute the second version of the platform infrastructure, which will be ready by the end of May 2019.

For the second prototype of the CPN platform, the implementation of the features has been prioritised in a way that allows us to follow the planned schedule, while adding meaningful functionalities that will also be improved and extended in future prototypes.

Subsequent versions of the platform components are expected to provide updated versions of the currently available bricks along with possible new bricks, in order to adapt to possible new requirements and functionalities needed by the constantly evolving CPN platform during the implementation phase of the project.

Read the full report on the "technology bricks" here. Stay tuned for our second CPN platform release!

(Image by Kvistholt Photography on Unsplash)

Test personalised news content with the CPN app!

Screen Shot 2019-05-07 at 10.56.09.png

As part of the second pilot, the CPN project is excited to welcome readers to experience and test news personalisation with the CPN app. This blog post will give an overview of pilot 2: the what, how & why.

Personalised news content from VRT, Deutsche Welle and Dias

We are inviting news readers to test the CPN app during a 4-week test period, starting in mid-May, with news content in the language of their choice - Dutch, English or Greek. Consortium partners VRT, Deutsche Welle and Dias have made their content available via the CPN app. When first launching the app, testers will be able to select their preferred language.

How to test the CPN app (Android only)

Interested in testing news personalisation with the CPN app? First register through the following links, and we will send you the details on how to download the app before the test period starts.

  • Click here to experience personalised news in Dutch

  • Click here to experience personalised news in Greek

  • Click here to experience personalised news in English

The app is currently only available on Android devices.

Expectations & next steps

During the test period, we might from time to time ask you to give your comments on the CPN app – feedback will be gathered via email and push notifications in the app. Thanks to the feedback from our testers, CPN will be able to improve and update the app and its recommendation software. As we also welcome media organisations to use the CPN software to personalise their own content, the feedback from readers is crucial in building a better personalised news experience.

Questions about the pilot? Contact us here!

Become a CPN pilot partner and join the next phase of news personalisation

Become a CPN pilot partner and join the next phase of news personalisation

CPN is looking for news organisations to personalise their news content in the CPN platform or integrate the CPN software in their own app! As a pilot partner, you are able to use the CPN software for free. CPN includes you in their communication channels and enables you to contribute to a personalisation software that takes into account your needs and ambitions.

Read More

From idea to concept: report from the CPN hackathon

The CPN hackathon gave tech and media companies the opportunity to learn about the CPN personalisation platform, and allowed them to kick-start their own collaborations that aim to build cutting-edge personalisation tools.


A broad range of tech and media professionals participated in the CPN hackathon in London on 13 and 14 February, hosted by Digital Catapult.

During two intense days, the hackathon participants learned about the CPN project and the technical architecture of the CPN recommender, and were able to participate in broader discussions about how news publishers could benefit from personalisation.

The event was also a chance for the participating media and tech companies to tackle news personalisation head-on: the participants started new collaborations with the aim of creating personalisation solutions that build on the CPN platform.

Six personalisation projects were launched at the hackathon. Over the next months the project teams will continue to develop their ideas further, with the aim of showcasing their solutions at the annual World News Media Congress, organised by WAN-IFRA in Glasgow in June.

Update: Read more about the six personalisation projects in the take away pack from the hackathon.

Day one: benefits of personalisation

Setting the scene for the event, Tilman Wagner, Innovation Manager at Deutsche Welle, started the hackathon by presenting the CPN project, its achievements so far, and the road ahead. While the first CPN prototype, created for desktop use, has already been tested during a pilot, the next step is developing a mobile version of the platform. (Read more about the first CPN prototype here.)

But why exactly should the news media care about personalisation? Titus Plattner, Senior Innovation Project Manager at Tamedia, offered a compelling argument by referring to his own company: the Swiss publisher produces about 1000 news articles every day across its different publications – but the average user reads only 2,4 of those. It’s clear that those articles need to be relevant to the reader, he said. Plattner also gave an overview of the various personalisation efforts that newsrooms around the world are trying out today. (Read more in his blog post here.)

While tech giants obviously lead in terms of investing in algorithms and personalisation, Plattner said that news media companies have one important advantage: “Tech companies don’t want to care about the content that’s on their platforms. News media profoundly cares about content.” News publishers should therefore use algorithms to support their existing cultures, rather than focus on building fully automated tools.

To conclude the first day, the participants were asked to think about the ideal future for content personalisation. What would it look like for the customer? What would it require from media organisations? These reflections formed the basis for the collaborative projects that were defined further the next day.

Day two: working towards solutions

The second day started with a deep dive into the technical features of the CPN platform: Nikos Sarris from ATC Innovation Lab, Fulvio D’Antonio from LiveTech, and Ferdinando Bosco from Engineering discussed the intricacies of the technologies that power the CPN platform. (For detailed descriptions of the platform’s infrastructure, microservices and technology bricks, check out the project Deliverables.)

The majority of the day was dedicated to workshop sessions that allowed the participants to develop their collaborations further. What challenges prevent media companies from embracing personalisation? What ways are there around these challenges?

Between workshop sessions, Olga Kisselmann, Innovation Manager at Deutsche Welle described how Germany’s public international broadcaster approaches personalisation. Given the range of its stakeholders and audiences, the company – which publishes content in 30 languages across 60 countries – takes a careful approach to new technologies. But Deutsche Welle believes that personalisation can increase content discovery from the company’s vast archives, and help it reach new audiences who might not be looking for news content specifically.

The day came to an end with the different groups presenting their ideas for news personalisation solutions. These varied greatly, from an automated content tagging solution to combining data from users’ social media accounts with data about their news consumption habits, and from taking on the filter bubble to incorporating a broad range of open-source data in the CPN personalisation algorithm.

The teams will now continue refining these ideas and work towards creating services that enhance the CPN platform and that will be presented in June at the World News Media Congress in Glasgow.

We will soon share more details about the collaborations that were started at the Hackathon – stay tuned!

The first CPN pilot is finished!

Almost 100 end-users tested the CPN news recommender platform during the first pilot phase. Here are the main takeaways from the pilot, information about the tested prototype, as well as details about the next steps.


The news recommender that the CPN project is developing will be iteratively tested and validated in operational real-life environments throughout the project in the three different pilot countries. The pilot countries are Belgium (coordinated by VRT), Germany (coordinated by Deutsche Welle) and Cyprus (coordinated by DIAS). Three main pilot tests will be organised at different stages, each adding a larger number of users as the developed proof of concept becomes more mature. We just finished the first pilot – read on to learn about the results!

What did we do in the first pilot?

In October and November 2018, we engaged almost 100 end-users to test our first prototype for a period of 10 days. Specifically, the participating end-users tested the web interface of the recommender. In each pilot country, the recommender contained news content from the local media partner (VRT, Deutsche Welle and DIAS).

The first CPN prototype consisted of three news sections, presented in separate tabs:

  • Most popular – the most-read content among the users of the particular news outlet

  • Latest news – all articles in chronological order, with the latest on top

  • Personalised – the most relevant content for the user

All end-users were free to use the recommender and read the three tabs as much as they wanted during the test period.

Screenshot of the recommender’s web interface in Belgium

Screenshot of the recommender’s web interface in Belgium

During the pilot, we tested the personalisation algorithm and evaluated the technical components. Furthermore, in a qualitative research track, we evaluated the user experience of the web application, and assessed the users’ expectations with regard to news personalisation and FOMO (Fear Of Missing Out). 56 end-users tested the prototype in Belgium, 21 in Cyprus and 20 in Germany. Feedback was gathered during and after the pilot test by means of online questionnaires, focus groups, interviews and ad hoc interactions with the research participants.

Setting focus group interview in Belgium

Setting focus group interview in Belgium

What are the main takeaways of the first pilot?

The “Personalised” tab was the most read stream in all three pilot countries. But while news personalisation itself was evaluated as positive, there was a big fear of missing out (FOMO) when receiving personalised news articles: the participants were afraid that through personalisation they might only get news content based on their interests, which could cause them to miss other relevant or important news. CPN tries to tackle this in two ways:

  • By providing a ‘Most Popular’ and ‘Latest News’ tabs in combination with the ‘Personalised’ tab, thus giving end-users control over which tab they read first.

  • By giving end-users a transparent insight and control over how their personalised news offer is created.

Another suggested way to deal with FOMO is to indicate an important or breaking news item in the personalised tab, e.g. by means of a notification or a bar at the bottom of the page. This option will be further explored and integrated in the second pilot.

The fact that the recommender is not available as a mobile application was a negative point among the testers. (The pilot phase 2 of CPN will specifically test a mobile application.) On the other hand, the participants generally thought the web interface was straightforward and easy to use, although some thought that more important articles could be made more prominent.

What’s next?

In 2019, two more pilots will be set up. Currently, we are working on a mobile application of the recommender that will be tested in pilot 2. While pilot 1 was a controlled (small) testing phase, for pilot 2 we will move to semi-controlled testing, and selected external participants will be able to try the platform at this point. Finally, pilot 3 will be fully open, so anyone interested in CPN can participate in the last pilot phase.

Do you want be among the first to test the platform? Fill in this form and we’ll contact you when pilot 2 will start!

Read the full report on the first CPN pilot here.