Research topic trend prediction of scientific papers based on spatial enhancement and dynamic graph convolution network
This addresses the need for researchers to identify future hotspots by improving prediction accuracy over existing methods, though it appears incremental as it builds on known spatiotemporal modeling techniques.
The paper tackles the problem of predicting future research topic trends by proposing a spatiotemporal convolutional network model that combines graph convolutional neural networks (GCN) and temporal convolutional networks (TCN) to capture spatial dependencies and temporal dynamics, achieving state-of-the-art performance on paper datasets.
In recent years, with the increase of social investment in scientific research, the number of research results in various fields has increased significantly. Accurately and effectively predicting the trends of future research topics can help researchers discover future research hotspots. However, due to the increasingly close correlation between various research themes, there is a certain dependency relationship between a large number of research themes. Viewing a single research theme in isolation and using traditional sequence problem processing methods cannot effectively explore the spatial dependencies between these research themes. To simultaneously capture the spatial dependencies and temporal changes between research topics, we propose a deep neural network-based research topic hotness prediction algorithm, a spatiotemporal convolutional network model. Our model combines a graph convolutional neural network (GCN) and Temporal Convolutional Network (TCN), specifically, GCNs are used to learn the spatial dependencies of research topics a and use space dependence to strengthen spatial characteristics. TCN is used to learn the dynamics of research topics' trends. Optimization is based on the calculation of weighted losses based on time distance. Compared with the current mainstream sequence prediction models and similar spatiotemporal models on the paper datasets, experiments show that, in research topic prediction tasks, our model can effectively capture spatiotemporal relationships and the predictions outperform state-of-art baselines.