Ting Jiang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ting Jiang has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Yuanhao Niu
Nanjing University of Finance and Economics, China
2 shared publications - Zhiheng Chen
Nanjing University of Finance and Economics, China
2 shared publications - Weichen Bai
Shandong University of Science and Technology, China
1 shared publication
Latest Publications
- Open Access
- 20 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1620-1627
Dynamic Feature Collaborative Variational Auto-Encoders for Academic Paper Recommendation
The rapid growth of scientific research has contributed to an overwhelming surge of information in academic papers, and scholarly paper recommendation systems have developed rapidly. However, existing systems often underutilize valuable feature information and fail to consider changes in the attractiveness of papers over time. Therefore, this paper proposes a novel approach called the dynamic feature-based collaborative variational auto-encoders (DFC-VGAE) model for the academic paper recommendation. In this study, we preprocess the features using a pre-trained natural language model and capture structural features through co-authorship and citation networks. The model also modifies the encoding and decoding. Promising results were achieved through a real-world experiment using a comprehensive academic paper recommendation dataset.
- 20 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1620-1627
Open AccessDynamic Feature Collaborative Variational Auto-Encoders for Academic Paper Recommendation
The rapid growth of scientific research has contributed to an overwhelming surge of information in academic papers, and scholarly paper recommendation systems have developed rapidly. However, existing systems often underutilize valuable feature information and fail to consider changes in the attractiveness of papers over time. Therefore, this paper proposes a novel approach called the dynamic feature-based collaborative variational auto-encoders (DFC-VGAE) model for the academic paper recommendation. In this study, we preprocess the features using a pre-trained natural language model and capture structural features through co-authorship and citation networks. The model also modifies the encoding and decoding. Promising results were achieved through a real-world experiment using a comprehensive academic paper recommendation dataset.
- Open Access
- 13 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 384-390
HTGAT: A Heterogeneous Temporal Graph Attention Network for Scholars’ Impact Prediction
The primary goal of scholarly impact prediction is to forecast the impact of a scholar and their potential scholarly achievements in future research careers, such as academic monitoring, awarding tenure to researchers, and identifying promising candidates for research grants. Thus, scholarly impact prediction plays a crucial role in investigating scientific impact. Current research has predominantly utilized citation metrics-based methods, which do not frequently utilize the extensive data available in the intricate nodes and connections of varied scholarly networks that develop over time. Nevertheless, this study introduces a fresh outlook by conducting research into extracting the implicit semantic and structural data in academic text content, found within the temporal and structural information of collaborative networks, to forecast the scientific impact of academics. In this paper, we present the HTGAT, a heterogeneous temporal graph attention model that merges the graph attention mechanism model with recurrent neural networks. The model's main objective is to enhance the accuracy of temporal predictions by effectively addressing the complex interaction between entities in multi-relational temporal graphs. Utilizing the nodes' representation in diverse academic networks, alongside the temporal information inferred from node relationships, to augment the modeling of scholarly influence, we conduct predictive and quantitative analyses on genuine academic data networks. Empirical results demonstrate that the method improves prediction performance in comparison to both benchmark and citation metrics-based techniques.
- 13 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 384-390
Open AccessHTGAT: A Heterogeneous Temporal Graph Attention Network for Scholars’ Impact Prediction
The primary goal of scholarly impact prediction is to forecast the impact of a scholar and their potential scholarly achievements in future research careers, such as academic monitoring, awarding tenure to researchers, and identifying promising candidates for research grants. Thus, scholarly impact prediction plays a crucial role in investigating scientific impact. Current research has predominantly utilized citation metrics-based methods, which do not frequently utilize the extensive data available in the intricate nodes and connections of varied scholarly networks that develop over time. Nevertheless, this study introduces a fresh outlook by conducting research into extracting the implicit semantic and structural data in academic text content, found within the temporal and structural information of collaborative networks, to forecast the scientific impact of academics. In this paper, we present the HTGAT, a heterogeneous temporal graph attention model that merges the graph attention mechanism model with recurrent neural networks. The model's main objective is to enhance the accuracy of temporal predictions by effectively addressing the complex interaction between entities in multi-relational temporal graphs. Utilizing the nodes' representation in diverse academic networks, alongside the temporal information inferred from node relationships, to augment the modeling of scholarly influence, we conduct predictive and quantitative analyses on genuine academic data networks. Empirical results demonstrate that the method improves prediction performance in comparison to both benchmark and citation metrics-based techniques.