A journal recommender for article submission using transformers

This work is about recommending the best journal for article submission to authors. The approach taken here is based on relevance determined through the application of neural network based natural language processing techniques to the abstracts of articles already accepted by journals. Title, keywords, and field of study are not needed in the approach outlined here. The significance of the relevancy of a journal is that an article published in a less relevant journal will have less exposure to the intended target audience, and consequently have less of an impact. The conceptual content contained in the abstracts of articles appearing in a journal can be used to characterize that journal. The main purpose of this work will be exploring neural network architectures for discovering and recommending appropriate journals to those seeking to publish their research. In this work, the current state of the art will be extended and a robust and generic article-to-journal matching tool for all publishers, using Web of Science data, is proposed and made public for the first time.