Topical keyphrase extraction with hierarchical semantic networks

Yoo yeon Sung, Seoung Bum Kim

Research output: Contribution to journalArticle

Abstract

Topical keyphrase extraction is used to summarize large collections of text documents. However, traditional methods cannot properly reflect the intrinsic semantics and relationships of keyphrases because they rely on a simple term-frequency-based process. Consequently, these methods are not effective in obtaining significant contextual knowledge. To resolve this, we propose a topical keyphrase extraction method based on a hierarchical semantic network and multiple centrality network measures that together reflect the hierarchical semantics of keyphrases. We conduct experiments on real data to examine the practicality of the proposed method and to compare its performance with that of existing topical keyphrase extraction methods. The results confirm that the proposed method outperforms state-of-the-art topical keyphrase extraction methods in terms of the representativeness of the selected keyphrases for each topic. The proposed method can effectively reflect intrinsic keyphrase semantics and interrelationships.

Original languageEnglish
Article number113163
JournalDecision Support Systems
Volume128
DOIs
Publication statusPublished - 2020 Jan

Keywords

  • Hierarchical networks
  • Phrase rankings
  • Semantic relationships
  • Text mining
  • Topical keyphrase extraction

ASJC Scopus subject areas

  • Management Information Systems
  • Information Systems
  • Developmental and Educational Psychology
  • Arts and Humanities (miscellaneous)
  • Information Systems and Management

Cite this

Topical keyphrase extraction with hierarchical semantic networks. / Sung, Yoo yeon; Kim, Seoung Bum.

In: Decision Support Systems, Vol. 128, 113163, 01.2020.

Research output: Contribution to journalArticle

@article{a1c93f252c2149e4b09e132653608bdf,
title = "Topical keyphrase extraction with hierarchical semantic networks",
abstract = "Topical keyphrase extraction is used to summarize large collections of text documents. However, traditional methods cannot properly reflect the intrinsic semantics and relationships of keyphrases because they rely on a simple term-frequency-based process. Consequently, these methods are not effective in obtaining significant contextual knowledge. To resolve this, we propose a topical keyphrase extraction method based on a hierarchical semantic network and multiple centrality network measures that together reflect the hierarchical semantics of keyphrases. We conduct experiments on real data to examine the practicality of the proposed method and to compare its performance with that of existing topical keyphrase extraction methods. The results confirm that the proposed method outperforms state-of-the-art topical keyphrase extraction methods in terms of the representativeness of the selected keyphrases for each topic. The proposed method can effectively reflect intrinsic keyphrase semantics and interrelationships.",
keywords = "Hierarchical networks, Phrase rankings, Semantic relationships, Text mining, Topical keyphrase extraction",
author = "Sung, {Yoo yeon} and Kim, {Seoung Bum}",
year = "2020",
month = "1",
doi = "10.1016/j.dss.2019.113163",
language = "English",
volume = "128",
journal = "Decision Support Systems",
issn = "0167-9236",
publisher = "Elsevier",

}

TY - JOUR

T1 - Topical keyphrase extraction with hierarchical semantic networks

AU - Sung, Yoo yeon

AU - Kim, Seoung Bum

PY - 2020/1

Y1 - 2020/1

N2 - Topical keyphrase extraction is used to summarize large collections of text documents. However, traditional methods cannot properly reflect the intrinsic semantics and relationships of keyphrases because they rely on a simple term-frequency-based process. Consequently, these methods are not effective in obtaining significant contextual knowledge. To resolve this, we propose a topical keyphrase extraction method based on a hierarchical semantic network and multiple centrality network measures that together reflect the hierarchical semantics of keyphrases. We conduct experiments on real data to examine the practicality of the proposed method and to compare its performance with that of existing topical keyphrase extraction methods. The results confirm that the proposed method outperforms state-of-the-art topical keyphrase extraction methods in terms of the representativeness of the selected keyphrases for each topic. The proposed method can effectively reflect intrinsic keyphrase semantics and interrelationships.

AB - Topical keyphrase extraction is used to summarize large collections of text documents. However, traditional methods cannot properly reflect the intrinsic semantics and relationships of keyphrases because they rely on a simple term-frequency-based process. Consequently, these methods are not effective in obtaining significant contextual knowledge. To resolve this, we propose a topical keyphrase extraction method based on a hierarchical semantic network and multiple centrality network measures that together reflect the hierarchical semantics of keyphrases. We conduct experiments on real data to examine the practicality of the proposed method and to compare its performance with that of existing topical keyphrase extraction methods. The results confirm that the proposed method outperforms state-of-the-art topical keyphrase extraction methods in terms of the representativeness of the selected keyphrases for each topic. The proposed method can effectively reflect intrinsic keyphrase semantics and interrelationships.

KW - Hierarchical networks

KW - Phrase rankings

KW - Semantic relationships

KW - Text mining

KW - Topical keyphrase extraction

UR - http://www.scopus.com/inward/record.url?scp=85074529522&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074529522&partnerID=8YFLogxK

U2 - 10.1016/j.dss.2019.113163

DO - 10.1016/j.dss.2019.113163

M3 - Article

AN - SCOPUS:85074529522

VL - 128

JO - Decision Support Systems

JF - Decision Support Systems

SN - 0167-9236

M1 - 113163

ER -