Mingxin Lu’s research while affiliated with Nanjing University and other places

Comprehensively extracting spatio-temporal features is essential to research topic trend prediction. This necessity arises from the fact that research topics exhibit both temporal trend features and spatial correlation features. This study proposes a Temporal Graph Attention Network (T-GAT) to extract the spatio-temporal features of research topics and predict their trends. In this model, a temporal convolutional layer is employed to extract temporal trend features from multivariate topic time series. Additionally, a multi-head graph attention layer is introduced to capture spatial correlation features among research topics. This layer learns attention scores from the data by using scaled dot product operations and updates edge weights between topics accordingly, thereby mitigating the issue of over-smoothing. Furthermore, we introduce WFtopic-econ and WFtopic-polit, two domain-specific datasets for Chinese research topics constructed from the Wanfang Academic Database. Extensive experiments demonstrate that T-GAT outperforms baseline models in prediction accuracy, with RMSE and MAE being reduced by 4.8% to 7.1% and 14.5% to 18.4%, respectively, while R2 improved by 4.8% to 7.9% across varying observation time steps on the WFtopic-econ dataset. Moreover, on the WFtopic-polit dataset, RMSE and MAE were reduced by 4.0% to 5.3% and 10.0% to 10.7%, respectively, and R2 improved by 7.6% to 14.4%. These results validate the effectiveness of integrating graph attention with temporal convolution to model the spatio-temporal evolution of research topics, providing a robust tool for scholarly trend analysis and decision making.

Predicting trends across multiple research topics presents a significant challenge for multivariate time series forecasting. In the temporal dimension, the fluctuation in popularity of individual research topics reveals trend features, while in the spatial dimension, the interdependence among frequently co-occurring research topics reveals correlation features. However, existing methods often overlook this spatial correlation feature or regard it as static and unchanging, leading to suboptimal prediction results. To address these shortcomings, this paper proposes a novel spatio-temporal graph neural network model, the Temporal Graph Attention Network (T-GAT). This model employs temporal convolution to extract the temporal trend features of research topics and utilizes multi-head graph attention to extract the spatial correlation features among these topics. Notably, the graph attention mechanism is capable of dynamically adjusting the weights of neighboring nodes based on the attention scores learned from the data, thereby reducing the risk of over-smoothing. Experiments conducted on the dataset from the Wanfang Academic Journal Database demonstrate that the proposed model outperforms baseline methods.