NTB Byline: an automatic article generator enabling journalists to generate hundreds or even thousands of automated articles from a single set of data and a push of a button!
Publisert: 11. august 2022

Olivia Louise Glittenberg from the NTB-team pitching their prototype at FutureWeek22. Video: Oliver Cameron. 

"Imagine you’re a journalist working at NTB, having to write hundreds of almost identical articles every time new data is published. Then new data is published every week or even every day, and so you have to write a hundred more. The same data, the same words. Slightly different numbers and regions. During the pandemic, statistics about the number of covid-19 cases were written and published every day. But NTB had help from an automated text generator - a robot journalist."

The prototype and concept Byline has been designed and developed by the students Even Berntsen, Olivia Louise Glittenberg, Trine Mjaatvedt, Henrik Samset, Birgitte Strand and Kamilla Wigestrand as a part of MIX250, the final course of Media- and Interaction design at the University of Bergen. The team collaborated with NTB, Norway’s leading provider of text, images, video and graphics to the Norwegian media.

The challenge

The challenge the team was presented with was to develop a tool that could generate hundreds of articles based on a single set of data and a push of a button. These articles would solve their customers' need for personalized content, and the tool would be based on AI, machine learning, language processing, and automatization. The goal is that Byline will create value for NTB as it would drastically improve efficiency in-house, making journalists able to generate articles at a rate never done before.

The team creating different ideas for the solution during the Design Sprint. Photo: from the project report.

Byline for NTB

NTB Byline is an automatic article generator for journalists at NTB. Byline elevates the basic tool that was used to generate covid-19 articles, enabling journalists at NTB to generate hundreds or even thousands of automated articles from just one data source. It allows journalists to choose datasets, edit the automatically generated articles and produce hundreds of articles that are ready for publishing within a few minutes. This tool streamlines journalistic work and helps journalists save time on articles with large amounts of data. Byline is a tool for all journalists regardless of their technical competence, and the prototype is therefore made as self-explanatory and easy to use as possible.


Members of the team and jury leader

The team with the jury leader Geir Terje Ruud at the MVP Award 2022. Photo: NCE

Byline was also the winners of this years MVP Award 2022 (Minimal viable product), which was judged by a jury consisting of representatives of the five Norwegian companies collaborating with this years students.






  • Read the project report HERE
  • Watch a demo for the prototype HERE

Publisert: 11. august 2022
linkedin facebook pinterest youtube rss twitter instagram facebook-blank rss-blank linkedin-blank pinterest youtube twitter instagram