Citation recommendation via proximity full-text citation analysis and supervised topical prior

Liu, Xiaozhong; Zhang, Jinsong; Guo, Chun

Permalink

https://hdl.handle.net/2142/89305 Copy

Description

Title

Citation recommendation via proximity full-text citation analysis and supervised topical prior

Author(s)

Liu, Xiaozhong; Zhang, Jinsong; Guo, Chun

Issue Date

2016-03-15

Keyword(s)

• bibliometrics
• citation recommendation
• supervised topic modeling
• PageRank
• prior knowledge

Abstract

Currently the many publications are now available electronically and online, which has had a significant effect, while brought several challenges. With the objective to enhance citation recommendation based on innovative text and graph mining algorithms along with full-text citation analysis, we utilized proximity-based citation contexts extracted from a large number of full-text publications, and then used a publication/citation topic distribution to generate a novel citation graph to calculate the publication topical importance. The importance score can be utilized as a new means to enhance the recommendation performance. Experiment with full-text citation data showed that the novel method could significantly (p < 0.001) enhance citation recommendation performance.

Publisher

iSchools

Series/Report Name or Number

IConference 2016 Proceedings

Type of Resource

text

Language

eng

Permalink

http://hdl.handle.net/2142/89305

DOI

https://doi.org/10.9776/16164

Copyright and License Information

Copyright 2016 is held by the authors. Copyright permissions, when appropriate, must be obtained directly from the authors.

Owning Collections