Recommending Scientific Collaboration from ResearchGate

What is it about?

Scientific collaboration improves researchers productivity by providing a way to share new ideas, learn new techniques, and find new research applications, increasing the chance to access funding. Beyond ethics and reciprocity, there are other important aspects on achieving scientific collaborations, such as research interests and expected productivity gain, that are paramount to a successful partnership. However, achieving effective collaborations is hard work and can drain researchers time. In this work, we propose a recommendation approach that uses different strategies to suggest scientific collaboration for researchers based on their research interest. In particular, our approach exploits ResearchGate, a well-known research social network from where research interests and researchers production are used to model similarity between them. Experimental results show that the content-based strategy outperforms neighborhood-based collaborative filtering strategies to recommend scientific collaboration with gains of up 16.60% in precision, 37.19% in the recall, and 21.16% in F1 for the top-20 recommendation lists.

Featured Image

Why is it important?

Scientific collaboration can improve researchers productivity by promoting the sharing of ideas, the learning of new techniques and applications for current research, which increases the chance to access research funding. Additionally, scientific collaboration can inspire researchers to move forward, mitigating frustration with demands of teaching and the bureaucratic burdens that the academic job entails. However, achieving and managing collaboration requires a genuine conversation between researchers about their research interests and how they may benefit each other. This is hard work and can drain researchers time. Thus, one of the main problems in achieving scientific collaboration is to identify collaborators with similar or complementary research interest.

Perspectives