Brain Activation-based Filtering: a Scholarly Journal Recommendation Model for Human Neuroimaging Studies

Abstract

The development of noninvasive neuroimaging techniques such as functional magnetic resonance imaging was followed by a large volume of human neuroimaging studies of mental processes, mechanisms, and diseases. Due to the high volume of studies and the large number of journals, it is increasingly challenging for neuroscientists to review existing scholarly journals and find the most suitable journal to publish their studies. Therefore, this paper proposes a scholarly journal recommendation model for human neuroimaging studies called brain activation-based filtering (BAF). Based on the collective matrix factorization technique, BAF recommends journals relevant to the activated brain regions that are described in a given neuroimaging study. For instance, if social brain regions such as the dorsomedial prefrontal cortex, precuneus, and temporoparietal junction are activated in a study, BAF recommends relevant social neuroscience journals (e.g., Social Cognitive and Affective Neuroscience). Five-fold cross-validation shows that BAF predicts journals with a reliable area under the curve score of 0.855. Furthermore, an interactive Google Colab notebook is offered to recommend relevant journals for a novel human neuroimaging study (https://github.com/JunsolKim/brain-activation-based-filtering).