Citation Trajectory Prediction via Publication Influence Representation Using Temporal Knowledge Graph

TL;DR

This paper introduces CTPIR, a novel framework for predicting citation trajectories by modeling publication influence through temporal knowledge graphs, effectively capturing implicit factors and handling cold-start scenarios.

Contribution

The paper presents CTPIR, a new influence representation framework utilizing temporal knowledge graphs for improved citation trajectory prediction, including a new patent-based dataset.

Findings

CTPIR outperforms existing methods in citation prediction accuracy.

The influence representation effectively captures citation momentum.

The approach works well on both academic and patent datasets.

Abstract

Predicting the impact of publications in science and technology has become an important research area, which is useful in various real world scenarios such as technology investment, research direction selection, and technology policymaking. Citation trajectory prediction is one of the most popular tasks in this area. Existing approaches mainly rely on mining temporal and graph data from academic articles. Some recent methods are capable of handling cold-start prediction by aggregating metadata features of new publications. However, the implicit factors causing citations and the richer information from handling temporal and attribute features still need to be explored. In this paper, we propose CTPIR, a new citation trajectory prediction framework that is able to represent the influence (the momentum of citation) of either new or existing publications using the history information of all their attributes. Our framework is composed of three modules: difference-preserved graph embedding, fine-grained influence representation, and learning-based trajectory calculation. To test the effectiveness of our framework in more situations, we collect and construct a new temporal knowledge graph dataset from the real world, named AIPatent, which stems from global patents in the field of artificial intelligence. Experiments are conducted on both the APS academic dataset and our contributed AIPatent dataset. The results demonstrate the strengths of our approach in the citation trajectory prediction task.