Constructing Topic Person Interaction Networks Using a Tree Kernel-Based Method

Yung-Chun Chang, Zhong-Yong Chen, Chien Chin Chen, Wen Lian Hsu

Research output: Contribution to journalArticle

14 Downloads (Pure)

Abstract

In this paper, we investigate the interactions
between topic persons to help readers construct the background
knowledge of a topic. We proposed a rich interactive tree
structure to represent syntactic, content, and semantic
information in the text for extracting person interactions.
Subsequently, a model-based EM method is employed to
discover the stance communities of the topic persons to assist
the exhibition of the interaction networks. Empirical
evaluations demonstrate that the proposed method is effective
in detecting and extracting the interactions between topic
persons in the text, and outperforms other extraction
approaches used for comparison. Furthermore, readers will be
able to easily navigate through the topic persons of interest
within the interaction networks, and further construct the
background knowledge of the topic to facilitate comprehension.
Index Terms—Topic summarization, interaction extraction,
person multi-polarization, stance community identification,
topic person interaction network.
Original languageEnglish
Pages (from-to)238-245
Number of pages8
JournalInternational Journal of Languages
Publication statusPublished - Dec 2015
Externally publishedYes

Fingerprint

Syntactics
Polarization

Cite this

Constructing Topic Person Interaction Networks Using a Tree Kernel-Based Method. / Chang, Yung-Chun; Chen, Zhong-Yong ; Chen, Chien Chin; Hsu, Wen Lian.

In: International Journal of Languages, 12.2015, p. 238-245.

Research output: Contribution to journalArticle

@article{e6188dba4e704461aa97f913dcc082f9,
title = "Constructing Topic Person Interaction Networks Using a Tree Kernel-Based Method",
abstract = "In this paper, we investigate the interactionsbetween topic persons to help readers construct the backgroundknowledge of a topic. We proposed a rich interactive treestructure to represent syntactic, content, and semanticinformation in the text for extracting person interactions.Subsequently, a model-based EM method is employed todiscover the stance communities of the topic persons to assistthe exhibition of the interaction networks. Empiricalevaluations demonstrate that the proposed method is effectivein detecting and extracting the interactions between topicpersons in the text, and outperforms other extractionapproaches used for comparison. Furthermore, readers will beable to easily navigate through the topic persons of interestwithin the interaction networks, and further construct thebackground knowledge of the topic to facilitate comprehension.Index Terms—Topic summarization, interaction extraction,person multi-polarization, stance community identification,topic person interaction network.",
author = "Yung-Chun Chang and Zhong-Yong Chen and Chen, {Chien Chin} and Hsu, {Wen Lian}",
year = "2015",
month = "12",
language = "English",
pages = "238--245",
journal = "International Journal of Languages",

}

TY - JOUR

T1 - Constructing Topic Person Interaction Networks Using a Tree Kernel-Based Method

AU - Chang, Yung-Chun

AU - Chen, Zhong-Yong

AU - Chen, Chien Chin

AU - Hsu, Wen Lian

PY - 2015/12

Y1 - 2015/12

N2 - In this paper, we investigate the interactionsbetween topic persons to help readers construct the backgroundknowledge of a topic. We proposed a rich interactive treestructure to represent syntactic, content, and semanticinformation in the text for extracting person interactions.Subsequently, a model-based EM method is employed todiscover the stance communities of the topic persons to assistthe exhibition of the interaction networks. Empiricalevaluations demonstrate that the proposed method is effectivein detecting and extracting the interactions between topicpersons in the text, and outperforms other extractionapproaches used for comparison. Furthermore, readers will beable to easily navigate through the topic persons of interestwithin the interaction networks, and further construct thebackground knowledge of the topic to facilitate comprehension.Index Terms—Topic summarization, interaction extraction,person multi-polarization, stance community identification,topic person interaction network.

AB - In this paper, we investigate the interactionsbetween topic persons to help readers construct the backgroundknowledge of a topic. We proposed a rich interactive treestructure to represent syntactic, content, and semanticinformation in the text for extracting person interactions.Subsequently, a model-based EM method is employed todiscover the stance communities of the topic persons to assistthe exhibition of the interaction networks. Empiricalevaluations demonstrate that the proposed method is effectivein detecting and extracting the interactions between topicpersons in the text, and outperforms other extractionapproaches used for comparison. Furthermore, readers will beable to easily navigate through the topic persons of interestwithin the interaction networks, and further construct thebackground knowledge of the topic to facilitate comprehension.Index Terms—Topic summarization, interaction extraction,person multi-polarization, stance community identification,topic person interaction network.

M3 - Article

SP - 238

EP - 245

JO - International Journal of Languages

JF - International Journal of Languages

ER -