With over 4,000 primary research papers published every day within the natural sciences, it can be overwhelming to try to keep up-to-date with the literature in a research field.
When we spoke with researchers – whether they were professors, PHD students, working for pharmaceutical companies or in government departments – they shared a common frustration: with limited time, they were struggling to find relevant papers.
The majority of these nature.com users that we surveyed in 2015 agreed that staying up-to-date takes a lot of hard work. And despite their best efforts, often juggling journal table of contents alerts, PubMed, Twitter and feeding from lab peers, most said that in a typical month they probably miss relevant papers.
Today, Springer Nature is pleased to announce the launch of an innovative service which we believe will significantly improve the workflows of researchers by saving time and enabling access to the most relevant content, allowing users to access a new way to keep up to date without visiting any new websites.
Recommended is a service which we believe will help all primary researchers in the natural sciences keep up to date with the literature that really matters to them. It is a personalised service that suggests relevant papers for users, regardless of publisher, based on what they have previously read across all Springer Nature services.
If we believe the paper is the right one for the reader, then we will recommend it.
Developing this service, a first for any publisher, has been a long careful journey – and all along the way we have worked with groups of researchers to ensure the service we develop actually makes a difference to the people whowill use it.
Powered by an adaptive algorithm, Recommended learns about users individual research interests by analysing the last 100 papers read across nature.com, SpringerLink and BioMed Central. Recommended then searches for similar primary papers to the users reading history, utilising over 45,000 journals (and 65 million papers) from CrossRef and PubMed.
These are then combined with data from other sources, such as Altmetric, to create a recommendation score that our service uses to pick the top primary research papers recommendations to deliver to users. Recommended continually learns and improves based on how the users interact with its suggestions.
Since March 2016 a beta version of Recommended has been running across selected journals and pages on our websites, and based on exceptional user statistics, backed up by extensive quantitative and qualitative user research, we are now pleased to roll out the service more widely.
Recommended is a unique service in the researcher’s toolkit as it learns about users individual research interests and doesn’t just match papers based on keyword analysis; this ensures our users get the best possible recommendations – irrespective of publisher.
To learn more about Recommended and sign up for personalised research recommendations please visit recommended.springernature.com
Recommended is a service in continual development, based on the needs of the researcher community, so please let us know what you think of the service at: email@example.com