Mendeley Suggest is an article recommender system for researchers. It’s designed to help them discover new research based on their short and long term interests and to keep them up-to-date with what’s popular and trending in their domains.
The first set of recommendations is based on all of the articles that you have added to your personal library in Mendeley. These recommendations are very good for me, as much of my recent work has been on recommender systems.
The second set of recommendations is based on activity in Mendeley’s community. It recommends articles that are important in your domain but not necessarily related to your immediate interests. It’s a nice tool for helping researchers to keep up-to-date with position papers and reviews that have made an impact in your broader domain which, in my case, is Computer Science.
The third set of recommendations is based on very recent activity. It recommends articles that are related to the last article added to your library. These recommendations are much more focussed than the first two carousels, and supports changing interests since it’s based on just the last article that you added. The last article that I added to my library was Pattern Recognition and Machine Learning by Chris Bishop and the recommendations are interesting.
The fourth carousel contains recommendations based on the last article that you read using any of Mendeley’s pdf readers (Desktop, Web and Mobile). This is complementary to the previous carousel as the last article that you add to your library and the last article that you actually opened up to read can be different. For example, you may have added/saved a number of articles to read later, and you have only recently started reading them in more depth or are starting to work again on a subject you had not actively worked on for some time. These documents might already be in your library, so the recently added feature would not be so useful, but having recommendations based on what you recently read would. In the example below, the last article that I read was A Scala Tutorial for Java programmers by Michel Schinz and Philipp Haller. The related articles are also useful.
Finally, the fifth carousel recommends articles that are trending in Mendeley’s community from your domain. This is similar to the popular carousel but more focussed on recent trends in reading habits from Mendeley’s community. As you’d expect for Computer Science, I’ve often seen work from Deep Learning appearing here lately.
By offering recommendations that serve a different set of use cases, Mendeley Suggest is designed to help researchers discover relevant research whether it helps them to narrow in on a particular topic or broaden your horizon.