Unleash the power of your archives

Natural Language Processing algorithms can identify entities in large amounts of text.

Archives are a real treasure trove for newsrooms and media outlets – housing facts, background information and story upon story of genuinely good reporting. But often, there are problems: the content is not easily accessible for reporters and editors, and the ability to search is limited to a “dumb” keyword-search.

This is where INJECT comes in. Because INJECT connects directly into your archive CMS, accessing your content is only a few clicks away.

INJECT uses state-of-the-art machine learning and text-mining tools like Natural Language Processing (NLP) and Named Entity Recognition to unleash the power of your news archive. Our software can easily identify places, individuals, companies, numbers etc.

Your reporters will get more relevant information, faster. They won’t have to re-invent the wheel again and again, journalists can paste a well-written paragraph from an archived story into their new one with just one click.

The three Norwegian newspapers Sunnhordland Avis, Hordaland Avis and Hallingdølen will be the first media outlets to implement the “smart” archives into their workflow. The newspapers are local and regional titles with a daily cirulation of 6500 – 8500 copies each.

Magne Kydland, the editor-in-chief of Sunnhordland:

“A newspaper’s digital archive is in fact a treasure in making future stories. But today we do not make enough use of this opportunity. So we are really looking forward to using this new tool to do this.”