FF-PRec: A Feature Fusion-Based Paper Recommendation Method on Academic Big Data of Heterogeneous Network

With the development of information technology, academic data has increased dramatically. Nowadays, recommendation algorithm is widely used for scholars to find useful information from massive data. However, due to the discrete data and complex semantic relationship in the academic network, existing recommendation algorithms have limitations in feature extraction and data sparsity, which bring negative impacts on recommendation accuracy and personalization. In order to solve the above problems, we propose FF-PRec, a paper recommendation method based on feature fusion in the academic network. First, FF-PRec implements graph representation learning and a natural language processing tool to extract network features and text features respectively. Two types of features are combined as the representation vectors of scholars and papers. Second, a meta-path is designed based on prior knowledge to guide semantic information extraction. To validate our proposed method, we conducted experiments on the AMiner dataset. The experimental results indicate that FF-PRec performs better than traditional methods in paper recommendation tasks and shows high accuracy and correlation.