.png){kind=icon}
.png){kind=icon}
Return
Enhancing citation recommendation using citation network embedding
.png){kind=icon}
PRE
AI
DOI：10.1007/s11192-021-04196-3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Automatic recommendation of citations has been a focal point of research in scholarly digital libraries. Many graph-based citation recommendation algorithms have been proposed; however, most of them utilize local citation behavior from the citation network that results in recommending papers in the same proximity as the query article. In this paper, we propose to capture the global citation behavior in the citation network and use it to enhance the citation recommendation performance. Specifically, we develop a novel citation network embedding algorithm, ConvCN, to encode the citation relationship among papers. We then propose to enhance existing graph-based citation recommendation algorithms by incorporating ConvCN to improve the recommendation efficacy. ConvCN has been shown to improve the citation recommendation performance by 44.86% and 34.87% on average in terms of Bpref and F-measure@20, respectively. The findings from this research not only confirm that global citation behavior could be additionally useful for improving the performance of traditional citation recommendation algorithms but also shed light on the possibility to adapt the proposed ConvCN algorithm for other recommendation tasks that rely on graph-like information such as items recommendation in social networks and people recommendation in referral networks.
Keywords:
Citation recommendation
Knowledge graph embedding
Convolutional neural networks
Graph representation learning
Journal
IF:
3.5
Papers:
8.1K
Citations:
2.2W