Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

Categories
Open research

Experience of using CORE Recommender – an interview

Background to CORE Recommender

Making the repository experience more rewarding for users is a continual endeavour for repository managers, and the CORE Recommender is designed to provide a simple and fast solution to help researchers discover relevant further reading. The CORE Recommender is a plugin for repositories, journals and web interfaces that provides article suggestions closely related to the articles that the user is actively reading.  The source of recommended data is the base of CORE, which consists of over 25 million full texts from CORE.

Interview

Today we have interviewed George Macgregor, Scholarly Publications & Research Data Manager at the University of Strathclyde. George is responsible for the Strathprints institutional repository and we asked him to share his experience of using the CORE Recommender.

Screenshot of CORE Recommender on https://strathprints.strath.ac.uk/
Screenshot of CORE Recommender on https://strathprints.strath.ac.uk/

Hi George, please could you introduce Strathprints to us?

We have a number of repositories at the University of Strathclyde, but the one that I have the most to do with is Strathprints. Strathprints is Strathclyde’s institutional repository, built on Eprints 3.4+.

How did you find out about the CORE Recommender? 

We were early implementers of the CORE Recommender, so I can’t remember exactly — but I was spurred-on to implement the tool on Strathprints after reading a CORE blog post. I was impressed at how recommendations were calculated and how the wider CORE dataset was being harnessed.

Why did you decide to install it at Strathprints? 

I think the beauty of the CORE Recommender on EPrints is that it has been made available as a plugin via the EPrints Bazaar and requires very little configuration. Installation of the plugin was therefore a no brainer. But there is a more general need to improve users’ experience of repositories, especially at a user interface level. Additional functionality or tools, such as the CORE Recommender, which are made available to users can assist with this objective and deliver a more rewarding experience for users. 

What can you tell us about the installation of the plugin?

As I mentioned already, installation of the plugin can be achieved through the EPrints Bazaar. In many ways the plugin operates straight ‘out of the box’, although there are some minor changes that some institutions might like to make within the plugin’s configuration.

Why is it useful for your institution to use CORE Recommender?

There are a number of reasons why the CORE Recommender is useful. Making the repository experience better for users is one. I think it is also important to be seen to be participating in — and taking advantage of — open scholarly infrastructure, like CORE. The CORE Recommender is one way of achieving this; it sends out a signal that Strathprints, along with the other services it takes advantage of, is a node within the wider open scholarly communications landscape.

What are the advantages of using the CORE Recommender?

Allowing users to share in the critical mass of open content which repositories have been able to gather, and which CORE has been able to aggregate. But also allowing them to discover potentially useful research content exposed by other repositories.

What would you say is the uniqueness of the CORE Recommender?

The dataset powering the CORE Recommender, and its algorithm for calculating similarity, is the principal unique factor. The CORE dataset is unique, as well as uniquely large — so recommendations are being computed across arguably the most detailed inventory of open content available, meaning that users have a higher potential to encounter open content which they may otherwise miss.

What was the CORE Recommender impact on your repository’s pages?

One of the most noticeable impacts relates to the amount of time visitors to Strathprints tend to ‘dwell’ on pages. We observed a 58% increase in the length of time unique visitors spent on Strathprints following implementation of the Recommender. In other words, incorporating the Recommender into Strathprints’ abstract pages gave users a reason to stay on the repository for longer, before leaving.

Would you like to improve this service? If so, in what way?

I can’t think of anything at the moment!

Why would you recommend other institutions to use CORE Recommender? 

I think the benefits of the CORE Recommender are self-evident to anyone who has used a repository that integrates with the CORE Recommender. Take a look at Strathprints, or the White Rose Repository, for example. But I would also suggest that its inclusion is an important part of the repository community demonstrating the power of open research, and open access more specifically. Repositories have contributed to the CORE dataset. It therefore makes sense to harness this data for other purposes, including recommendation engines to support users in discovering new content. 

Currently, more than 90 recommender instances are used daily, ranging from institutional repositories like Strathprints,  disciplinary repositories like arXiv, and various other websites around the internet. Last month the CORE Recommender had successfully suggested 1.3million times additional content to users.

You can install CORE Recommender via the CORE Repository Dashboard and get a user feedback system that improves the recommendation accuracy based on metadata records or full text items or both.

The CORE Team

Share and Enjoy !

Shares

Leave a Reply

Your email address will not be published. Required fields are marked *