Enhancing accuracy and diversity of recommendation for interdisciplinary journals: A deep learning approach

Abstract

To meet scholars’ need to recommend both higher accuracy and diversity when submitting interdisciplinary papers, this article proposes an improved journal diversity recommendation method based on the attention mechanism in deep learning. This method can retain all key information in long texts by using the attention mechanism. Five deep learning models based on attention mechanism are introduced, 104,176 paper abstracts from 111 Web of Science journals are used to fine-tune the models by extracting research topics for nine journal types in the interdisciplinary category. After learning on training set and model testing on the test set, recommendation accuracy and diversity results are calculated for interdisciplinary journals. Finally, the recommendation accuracy and diversity of the five attention-based deep learning models are compared with benchmark models across different journal types. The experimental results demonstrate that the deep learning method can enhance the accuracy and diversity when recommending interdisciplinary journals at a large scale. It provides theoretical and practical advancements to develop an effective journal recommender system which helps scholars to make wise decision for journal submission.