A corpus-based approach to classifying emotions using Korean linguistic features

Younghee Jung, Kinam Park, Taemin Lee, Jeongmin Chae, Soon Young Jung

Research output: Contribution to journalArticle

Abstract

Recently, social network services have become the popular communication tools among internet and mobile users. And it has been shared various opinions, which could be included various emotions. Emotion analysis aims to extract various emotion information, such as joy, happy, funny, fear, sad, and lonely, and so on, from texts expressed in natural language. Previous studies about emotion analysis on texts written in Korean have focused generally on the basic sentiments such as positive/neutral/negative preferences or 4–10 emotion classes. In this paper, we propose an emotion analysis method based on supervised learning to classify various emotions from messages written in Korean. We had found the feature set optimized to each emotion class through evaluating the combinations of various linguistic features and built a model to classify the emotion using the optimized feature set. To do this, it was constructed the corpus that is manually annotated with 25 emotion classes. We performed a 10-fold cross variation experiment for evaluating the performance of the proposed method. Our method obtained F-value ranged from 73.1 to 98.0% for each of 25 emotion classes. The optimized feature sets for most of emotion classes include commonly word 2-gram, POS 1-gram, and character 1-gram feature.

Original languageEnglish
Pages (from-to)583-595
Number of pages13
JournalCluster Computing
Volume20
Issue number1
DOIs
Publication statusPublished - 2017 Mar 1

Fingerprint

Supervised learning
Linguistics
Internet
Communication
Experiments

Keywords

  • Emotion analysis
  • Emotion classification
  • Emotion recognition
  • Message

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications

Cite this

A corpus-based approach to classifying emotions using Korean linguistic features. / Jung, Younghee; Park, Kinam; Lee, Taemin; Chae, Jeongmin; Jung, Soon Young.

In: Cluster Computing, Vol. 20, No. 1, 01.03.2017, p. 583-595.

Research output: Contribution to journalArticle

Jung, Younghee ; Park, Kinam ; Lee, Taemin ; Chae, Jeongmin ; Jung, Soon Young. / A corpus-based approach to classifying emotions using Korean linguistic features. In: Cluster Computing. 2017 ; Vol. 20, No. 1. pp. 583-595.
@article{4cb0d5021457448c878b832092eb18a7,
title = "A corpus-based approach to classifying emotions using Korean linguistic features",
abstract = "Recently, social network services have become the popular communication tools among internet and mobile users. And it has been shared various opinions, which could be included various emotions. Emotion analysis aims to extract various emotion information, such as joy, happy, funny, fear, sad, and lonely, and so on, from texts expressed in natural language. Previous studies about emotion analysis on texts written in Korean have focused generally on the basic sentiments such as positive/neutral/negative preferences or 4–10 emotion classes. In this paper, we propose an emotion analysis method based on supervised learning to classify various emotions from messages written in Korean. We had found the feature set optimized to each emotion class through evaluating the combinations of various linguistic features and built a model to classify the emotion using the optimized feature set. To do this, it was constructed the corpus that is manually annotated with 25 emotion classes. We performed a 10-fold cross variation experiment for evaluating the performance of the proposed method. Our method obtained F-value ranged from 73.1 to 98.0{\%} for each of 25 emotion classes. The optimized feature sets for most of emotion classes include commonly word 2-gram, POS 1-gram, and character 1-gram feature.",
keywords = "Emotion analysis, Emotion classification, Emotion recognition, Message",
author = "Younghee Jung and Kinam Park and Taemin Lee and Jeongmin Chae and Jung, {Soon Young}",
year = "2017",
month = "3",
day = "1",
doi = "10.1007/s10586-017-0777-8",
language = "English",
volume = "20",
pages = "583--595",
journal = "Cluster Computing",
issn = "1386-7857",
publisher = "Kluwer Academic Publishers",
number = "1",

}

TY - JOUR

T1 - A corpus-based approach to classifying emotions using Korean linguistic features

AU - Jung, Younghee

AU - Park, Kinam

AU - Lee, Taemin

AU - Chae, Jeongmin

AU - Jung, Soon Young

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Recently, social network services have become the popular communication tools among internet and mobile users. And it has been shared various opinions, which could be included various emotions. Emotion analysis aims to extract various emotion information, such as joy, happy, funny, fear, sad, and lonely, and so on, from texts expressed in natural language. Previous studies about emotion analysis on texts written in Korean have focused generally on the basic sentiments such as positive/neutral/negative preferences or 4–10 emotion classes. In this paper, we propose an emotion analysis method based on supervised learning to classify various emotions from messages written in Korean. We had found the feature set optimized to each emotion class through evaluating the combinations of various linguistic features and built a model to classify the emotion using the optimized feature set. To do this, it was constructed the corpus that is manually annotated with 25 emotion classes. We performed a 10-fold cross variation experiment for evaluating the performance of the proposed method. Our method obtained F-value ranged from 73.1 to 98.0% for each of 25 emotion classes. The optimized feature sets for most of emotion classes include commonly word 2-gram, POS 1-gram, and character 1-gram feature.

AB - Recently, social network services have become the popular communication tools among internet and mobile users. And it has been shared various opinions, which could be included various emotions. Emotion analysis aims to extract various emotion information, such as joy, happy, funny, fear, sad, and lonely, and so on, from texts expressed in natural language. Previous studies about emotion analysis on texts written in Korean have focused generally on the basic sentiments such as positive/neutral/negative preferences or 4–10 emotion classes. In this paper, we propose an emotion analysis method based on supervised learning to classify various emotions from messages written in Korean. We had found the feature set optimized to each emotion class through evaluating the combinations of various linguistic features and built a model to classify the emotion using the optimized feature set. To do this, it was constructed the corpus that is manually annotated with 25 emotion classes. We performed a 10-fold cross variation experiment for evaluating the performance of the proposed method. Our method obtained F-value ranged from 73.1 to 98.0% for each of 25 emotion classes. The optimized feature sets for most of emotion classes include commonly word 2-gram, POS 1-gram, and character 1-gram feature.

KW - Emotion analysis

KW - Emotion classification

KW - Emotion recognition

KW - Message

UR - http://www.scopus.com/inward/record.url?scp=85013993579&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013993579&partnerID=8YFLogxK

U2 - 10.1007/s10586-017-0777-8

DO - 10.1007/s10586-017-0777-8

M3 - Article

AN - SCOPUS:85013993579

VL - 20

SP - 583

EP - 595

JO - Cluster Computing

JF - Cluster Computing

SN - 1386-7857

IS - 1

ER -