Institute of Electrical and Electronics Engineers (IEEE)

Research on keyword extraction based on Word2Vec weighted TextRank

Yujun Wen ¹

Hui Yuan ²

Pengzhou Zhang ³

Hide authors affiliations Show authors affiliations: 3 affiliations

[School of Computer Science, Communication University Of China, Beijing, China] |

New Media Institute Communication, University of China, Beijing, China |

[Faculty of Science and Technology, Communication University of China, Beijing, China] |

Publication type: Proceedings Article

Publication date: 2016-10-01

Institute of Electrical and Electronics Engineers (IEEE)

DOI: 10.1109/CompComm.2016.7925072

Copy DOI

Abstract

In this paper, we do a research on the keyword extraction method of news articles. We build a candidate keywords graph model based on the basic idea of TextRank, use Word2Vec to calculate the similarity between words as transition probability of nodes' weight, calculate the word score by iterative method and pick the top N of the candidate keywords as the final results. Experimental results show that the weighted TextRank algorithm with correlation of words can improve performance of keyword extraction generally.

Found

Top-30

Journals

	1
Applied Intelligence	Applied Intelligence, 1, 16.67% Applied Intelligence 1 publication, 16.67%
Expert Systems with Applications	Expert Systems with Applications, 1, 16.67% Expert Systems with Applications 1 publication, 16.67%
Technological Forecasting and Social Change	Technological Forecasting and Social Change, 1, 16.67% Technological Forecasting and Social Change 1 publication, 16.67%
IEEE Transactions on Emerging Topics in Computing	IEEE Transactions on Emerging Topics in Computing, 1, 16.67% IEEE Transactions on Emerging Topics in Computing 1 publication, 16.67%
Springer Series in Advanced Manufacturing	Springer Series in Advanced Manufacturing, 1, 16.67% Springer Series in Advanced Manufacturing 1 publication, 16.67%
	1

Publishers

	1 2
Springer Nature	Springer Nature, 2, 33.33% Springer Nature 2 publications, 33.33%
Elsevier	Elsevier, 2, 33.33% Elsevier 2 publications, 33.33%
Institute of Electrical and Electronics Engineers (IEEE)	Institute of Electrical and Electronics Engineers (IEEE), 2, 33.33% Institute of Electrical and Electronics Engineers (IEEE) 2 publications, 33.33%
	1 2

We do not take into account publications without a DOI.
Statistics recalculated weekly.

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.

Metrics

Publisher

Institute of Electrical and Electronics Engineers (IEEE)