What we learned from VRT MyNWS: a pilot on news personalisation at the Flemish public broadcaster

/
image (3).png

At the end of March, the innovation and news department of the Flemish public broadcaster VRT experimented for four weeks with VRT MyNWS. This web application was built and tested as part of CPN and aimed to bring the VRT readers articles based on their interests. After the launch of VRT MyNWS, 949 testers subscribed to give feedback on their experience of personalisation, the usage of the web app and the display of articles. Read on to find out what we learned.

VRT MyNWS: a web app customised to readers

In order to measure whether people are better informed when they receive recommendations or not, the project team built the web app VRT MyNWS, resembling to the general news website of VRT NWS. News articles in the new web app could be found under three different tabs:

  • My news: personalised articles

  • Headlines: articles selected by the news department

  • Just in: most recently published articles

During one month, testers could give feedback via a button in the app, participate in surveys and were kept up to date via a weekly mailing. Overall, the team received over 200 emails with suggestions for improving the app. These mostly concerned the user interface and the recommendation algorithm. On a daily basis, a team of developers processed the feedback.

“It was extremely informative to gather input from end users, as well as the news department, and link those two into practice. Only by working together and experimenting on the production floor, we are able to innovate.”- Ilke Lemmelijn, CPN project coordinator.

Personalisation based on artificial intelligence and popularity

The testing with VRT MyNWS took place in two phases. In the first phase of the experiment, the tab ‘My news’ was loaded with articles that were selected according to three algorithms: collaborative filtering, content-based recommending and a random selection of recent articles. By collaborative filtering, readers received news articles that other readers with similar interests also found interesting. By content-based recommending, articles were selected and offered on the basis of the content and metadata of the articles. Lastly, by including a random selection of articles, the project team aimed to avoid readers receiving too many similar articles and ending up in a so-called filter bubble. The testers were divided into two groups that each received their own composition of the three algorithms.

In a second phase of the testing period, the project team chose to recommend articles based on their popularity during a certain timeframe. The team wanted to find out what the ideal timeframe would be. Testers were once again divided into three groups, each receiving popular articles from the last hour, the last 12 hours or the last two days. The results showed that testers appreciated it more when they received articles that were popular during the last hour, rather than for a longer period.

Feedback on the user interface and the algorithm

Based on the click behaviour, testers seemed to appreciate the simple algorithm from the second phase more than the complex system from the first phase. As such, the tab ‘My news’ was used 68% as opposed to other tabs in the second phase, while it was used 38% in the first phase. During the second phase, testers also used the 'My news' tab more when they were shown popular articles from the last hour old. Overall, testers said that they felt better informed in the second phase.

During the first phase, the user feedback mostly concerned the user interface, such as the width of articles, and the recommendation algorithm, such as irrelevant news. In both phases, the publication date of the articles appeared to be an important factor in personalisation. Apart from the small amount of relevant, older articles, the majority of testers preferred to read articles that are no more than two days old.

“Unique for recommendations in the news area is that the age of the articles is crucial in maintaining the interest of readers.” - Joris Mattheijssens, Data scientist at CPN and VRT Innovation

The next step for news personalisation at VRT

The insights and results of the VRT MyNWS test are further processed within CPN. The CPN team also calls out to other European news organisations to personalise their news stories with the software from CPN. In a new pilot, the Cypriot news organisation Dias and Deutsche Welle are also experimenting with the personalisation of their news articles. The insights and next steps will be published here.

Interested in piloting the CPN software? Contact us here!

Discover the “technology bricks” that power the CPN platform

/
kvistholt-photography-191153-unsplash.jpg

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.

IMG_3290.JPG

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!