TY - GEN

T1 - Longitudinal Citation Prediction using Temporal Graph Neural Networks

AU - Nugaard Holm, Andreas

AU - Plank, Barbara

AU - Wright, Dustin

AU - Augenstein, Isabelle

PY - 2022

Y1 - 2022

N2 - Citation count prediction is the task of predicting the number of citations a paper has gained after a period of time. Prior work viewed this as a static prediction task. As papers and their citations evolve over time, considering the dynamics of the number of citations over time seems the logical next step. Here, we introduce the task of sequence citation prediction. The goal is to accurately predict the trajectory of the number of citations a scholarly work receives over time. We propose to view papers as a structured network of citations, allowing us to use topological information as a learning signal. Additionally, we learn how this dynamic citation network changes over time and the impact of paper meta-data such as authors, venues and abstracts. To approach the new task, we derive a dynamic citation network from Semantic Scholar spanning over 42 years. We present a model which exploits topological and temporal information using graph convolution networks paired with sequence prediction, and compare it against mul- tiple baselines, testing the importance of topological and tem- poral information and analyzing model performance. Our experiments show that leveraging both the temporal and topo- logical information greatly increases the performance of pre- dicting citation counts over time.

AB - Citation count prediction is the task of predicting the number of citations a paper has gained after a period of time. Prior work viewed this as a static prediction task. As papers and their citations evolve over time, considering the dynamics of the number of citations over time seems the logical next step. Here, we introduce the task of sequence citation prediction. The goal is to accurately predict the trajectory of the number of citations a scholarly work receives over time. We propose to view papers as a structured network of citations, allowing us to use topological information as a learning signal. Additionally, we learn how this dynamic citation network changes over time and the impact of paper meta-data such as authors, venues and abstracts. To approach the new task, we derive a dynamic citation network from Semantic Scholar spanning over 42 years. We present a model which exploits topological and temporal information using graph convolution networks paired with sequence prediction, and compare it against mul- tiple baselines, testing the importance of topological and tem- poral information and analyzing model performance. Our experiments show that leveraging both the temporal and topo- logical information greatly increases the performance of pre- dicting citation counts over time.

KW - Citation count prediction

KW - Dynamic citation network

KW - Graph convolution networks

KW - Topological information

KW - Temporal information

KW - Citation count prediction

KW - Dynamic citation network

KW - Graph convolution networks

KW - Topological information

KW - Temporal information

M3 - Article in proceedings

BT - AAAI 2022 Workshop on Scientific Document Understanding (SDU 2022)

PB - AAAI Press

ER -