Newsadoo

“Spotify for News”

From challenges to solutions
Challenge

Bring the attention of the readers back from Youtube, Fortnite and the like to the events of the world.

Idea

Use Natural Language Processing and Artificial Intelligence to filter, bundle and understand incoming news articles. Use this information to match the content to the news consumers.

Solution

Newsadoo offers its readers a personalized, multi-platform news timeline in just one service.

Challenge

Bring the attention of the readers back from Youtube, Tinder, Fortnite and the like to the events of the world. Due to long loading times of websites and an unmanageable amount of information, active news consumption loses relevance.

Idea

The use of Natural Language Processing and Artificial Intelligence allows us to model news content in a machine-understandable way. A matching algorithm decides which news reaches the user on whatever platform.

Solution

Together Newsadoo and Catalysts have built an AI-powered news processing pipeline. Incoming articles are put through data preparation, natural language processing/understanding, and classification steps.

Collection

News can be found all over the Internet. Thousands of websites and other electronic media channels publish updates on millions of topics. To gather all that information we developed push and pull based mechanisms that assure that all relevant media coverage is ingested into the Newsadoo news pool.

Extraction

After having the articles in our news pool we apply different information extraction algorithms to extract Tags, Locations, Sentiment and more.

Categorization

Finding relevant information within this enormous news corpus would be very hard without having categories. To automatically assign incoming articles to news categories we transform the articles into machine comprehensible vector representation and apply machine learning models to them.

Bundling

Often there are only a few sources of first-hand information but many news sources covering the situation. This puts users in the uncomfortable situation of having to go through repetitive content. To take this burden off the user we mitigate this problem by using natural language comparison techniques to group articles with similar content to bundles.

Overview & Details

Which do you prefer: short news briefing with important facts, or detailed analysis? By using models of language information theory we can present topics in the right level of detail, depending on device and situation.

Team

Catalysts develops individual software solutions, with a focus on high performance computing, scalability and reliability. The software systems for this project were developed, validated, deployed and hosted by Catalysts, leveraging the vast variety of in house experts.

Newsadoo is an Austrian Startup.
www.newsadoo.com

Vision
  • Have a look at your personal news timeline on Newsadoo.
  • Are you interested in how Machine Learning / Natural Language Processing / User Specific Recommendation can be applied to your use-case?
  • Are you interested in how we design/develop/deliver cloud-native multi-platform applications?

Your contact person

Martin Weber

Team Lead in Emerging Technologies

martin.weber@catalysts.cc

Profile on Xing, LinkedIn

Share this page:
Did you like this project? Sign up and receive more news:

Other projects

Menu