Powered by an adaptive algorithm, Recommended learns about your individual research interests by analysing the last 100 papers you’ve read across nature.com, SpringerLink and BioMed Central.
Recommended then looks for similar primary papers to your reading history, utilising approximately 45,000 journals from Crossref and PubMed. These get combined with data from other sources, such as Altmetric, to create a recommendation score which our service uses to deliver primary papers that meet the quality threshold, from all publishers.
Recommended continually learns and improves from how users interact with its suggestions.Start receiving recommendations
Because Recommended learns about your individual research interests and doesn’t just match papers based on keyword analysis, this ensures you get the best possible recommendations for you - irrespective of the publisher.
You can also tailor the service to your convenience, choosing how you receive your recommendations and the frequency.Start saving time
As our service learns about your individual research interests you'll start to receive weekly emails.
We would love to hear your feedback to help us shape and improve the service. Please email us at email@example.com.
We are currently looking for developers who are positive, keen to learn, happy to muck in with front & back end code, and who are professional and thoughtful.
Our team is small, flexible and values discussion. We believe that:
Situated in the heart of the Knowledge Quarter in Kings Cross, London, we're committed to supporting researchers with the work they do by building the best tools to solve their problems.
We believe we're onto something with Recommended, but we need your help to continue our success.
If this sounds interesting, send your CV to: firstname.lastname@example.org.
The Recommended team is part of Springer Nature digital.