Sentiment-property extraction using Korean syntactic features

Won Hee Yu, Yeongwook Yang, Ki Nam Park, Heui Seok Lim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Since Korean sentence structure generally has a predicate expressing a sentiment at the end, it is necessary to find out the correct property the predicate explains in a sentence. This study presents a sentiment-property extraction model that can reflect the features of the Korean syntax to find out a correct sentiment-property pair. The model uses a Korean parser to find out the property word dependent on a possible sentiment word in the parsed sentence and extracts the two words to make a sentiment-property pair when they are likely to form a pair. The test set yielded a precision ratio of 93% and recall ratio of 75%.

Original languageEnglish
Title of host publicationLecture Notes in Electrical Engineering
Pages23-30
Number of pages8
Volume179 LNEE
EditionVOL. 2
DOIs
Publication statusPublished - 2012 Oct 9
Event7th FTRA International Conference on Future Information Technology, FutureTech 2012 - Vancouver, BC, Canada
Duration: 2012 Jun 262012 Jun 28

Publication series

NameLecture Notes in Electrical Engineering
NumberVOL. 2
Volume179 LNEE
ISSN (Print)18761100
ISSN (Electronic)18761119

Other

Other7th FTRA International Conference on Future Information Technology, FutureTech 2012
CountryCanada
CityVancouver, BC
Period12/6/2612/6/28

Fingerprint

Syntactics

Keywords

  • extraction
  • Korean
  • parser
  • sentiment

ASJC Scopus subject areas

  • Industrial and Manufacturing Engineering

Cite this

Yu, W. H., Yang, Y., Park, K. N., & Lim, H. S. (2012). Sentiment-property extraction using Korean syntactic features. In Lecture Notes in Electrical Engineering (VOL. 2 ed., Vol. 179 LNEE, pp. 23-30). (Lecture Notes in Electrical Engineering; Vol. 179 LNEE, No. VOL. 2). https://doi.org/10.1007/978-94-007-5064-7_4

Sentiment-property extraction using Korean syntactic features. / Yu, Won Hee; Yang, Yeongwook; Park, Ki Nam; Lim, Heui Seok.

Lecture Notes in Electrical Engineering. Vol. 179 LNEE VOL. 2. ed. 2012. p. 23-30 (Lecture Notes in Electrical Engineering; Vol. 179 LNEE, No. VOL. 2).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yu, WH, Yang, Y, Park, KN & Lim, HS 2012, Sentiment-property extraction using Korean syntactic features. in Lecture Notes in Electrical Engineering. VOL. 2 edn, vol. 179 LNEE, Lecture Notes in Electrical Engineering, no. VOL. 2, vol. 179 LNEE, pp. 23-30, 7th FTRA International Conference on Future Information Technology, FutureTech 2012, Vancouver, BC, Canada, 12/6/26. https://doi.org/10.1007/978-94-007-5064-7_4
Yu WH, Yang Y, Park KN, Lim HS. Sentiment-property extraction using Korean syntactic features. In Lecture Notes in Electrical Engineering. VOL. 2 ed. Vol. 179 LNEE. 2012. p. 23-30. (Lecture Notes in Electrical Engineering; VOL. 2). https://doi.org/10.1007/978-94-007-5064-7_4
Yu, Won Hee ; Yang, Yeongwook ; Park, Ki Nam ; Lim, Heui Seok. / Sentiment-property extraction using Korean syntactic features. Lecture Notes in Electrical Engineering. Vol. 179 LNEE VOL. 2. ed. 2012. pp. 23-30 (Lecture Notes in Electrical Engineering; VOL. 2).
@inproceedings{5aaa6206e4a84446aced116a1221dcce,
title = "Sentiment-property extraction using Korean syntactic features",
abstract = "Since Korean sentence structure generally has a predicate expressing a sentiment at the end, it is necessary to find out the correct property the predicate explains in a sentence. This study presents a sentiment-property extraction model that can reflect the features of the Korean syntax to find out a correct sentiment-property pair. The model uses a Korean parser to find out the property word dependent on a possible sentiment word in the parsed sentence and extracts the two words to make a sentiment-property pair when they are likely to form a pair. The test set yielded a precision ratio of 93{\%} and recall ratio of 75{\%}.",
keywords = "extraction, Korean, parser, sentiment",
author = "Yu, {Won Hee} and Yeongwook Yang and Park, {Ki Nam} and Lim, {Heui Seok}",
year = "2012",
month = "10",
day = "9",
doi = "10.1007/978-94-007-5064-7_4",
language = "English",
isbn = "9789400750630",
volume = "179 LNEE",
series = "Lecture Notes in Electrical Engineering",
number = "VOL. 2",
pages = "23--30",
booktitle = "Lecture Notes in Electrical Engineering",
edition = "VOL. 2",

}

TY - GEN

T1 - Sentiment-property extraction using Korean syntactic features

AU - Yu, Won Hee

AU - Yang, Yeongwook

AU - Park, Ki Nam

AU - Lim, Heui Seok

PY - 2012/10/9

Y1 - 2012/10/9

N2 - Since Korean sentence structure generally has a predicate expressing a sentiment at the end, it is necessary to find out the correct property the predicate explains in a sentence. This study presents a sentiment-property extraction model that can reflect the features of the Korean syntax to find out a correct sentiment-property pair. The model uses a Korean parser to find out the property word dependent on a possible sentiment word in the parsed sentence and extracts the two words to make a sentiment-property pair when they are likely to form a pair. The test set yielded a precision ratio of 93% and recall ratio of 75%.

AB - Since Korean sentence structure generally has a predicate expressing a sentiment at the end, it is necessary to find out the correct property the predicate explains in a sentence. This study presents a sentiment-property extraction model that can reflect the features of the Korean syntax to find out a correct sentiment-property pair. The model uses a Korean parser to find out the property word dependent on a possible sentiment word in the parsed sentence and extracts the two words to make a sentiment-property pair when they are likely to form a pair. The test set yielded a precision ratio of 93% and recall ratio of 75%.

KW - extraction

KW - Korean

KW - parser

KW - sentiment

UR - http://www.scopus.com/inward/record.url?scp=84867078003&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867078003&partnerID=8YFLogxK

U2 - 10.1007/978-94-007-5064-7_4

DO - 10.1007/978-94-007-5064-7_4

M3 - Conference contribution

AN - SCOPUS:84867078003

SN - 9789400750630

VL - 179 LNEE

T3 - Lecture Notes in Electrical Engineering

SP - 23

EP - 30

BT - Lecture Notes in Electrical Engineering

ER -