Build emotion lexicon from microblogs by combining effects of seed words and emoticons in a heterogeneous graph

Kaisong Song, Shi Feng, Wei Gao, Daling Wang, Ling Chen, Chengqi Zhang

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

As an indispensable resource for emotion analysis, emotion lexicons have attracted increasing attention in recent years. Most existing methods focus on capturing the single emotional effect of words rather than the emotion distributions which are helpful to model multiple complex emotions in a subjective text. Meanwhile, automatic lexicon building methods are overly dependent on seed words but neglect the effect of emoticons which are natural graphical labels of fine-grained emotion. In this chapter, we describe a novel emotion lexicon building framework that leverages both seed words and emoticons simultaneously to capture emotion distributions of candidate words more accurately. Our method overcomes the weakness of existing methods by combining the effects of both seed words and emoticons in a unified three-layer heterogeneous graph, in which a multi-label random walk (MLRW) algorithm is performed to strengthen the emotion distribution estimation. Experimental results on real-world data reveal that our constructed emotion lexicon achieves promising results for emotion classification compared to the state-of-the-art lexicons.

Original languageEnglish
Title of host publicationSocial Media Content Analysis
Subtitle of host publicationNatural Language Processing and Beyond
PublisherWorld Scientific Publishing Co. Pte Ltd
Pages171-195
Number of pages25
ISBN (Electronic)9789813223615
ISBN (Print)9789813223608
DOIs
Publication statusPublished - 1 Jan 2017

Fingerprint

Seed
Labels

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Song, K., Feng, S., Gao, W., Wang, D., Chen, L., & Zhang, C. (2017). Build emotion lexicon from microblogs by combining effects of seed words and emoticons in a heterogeneous graph. In Social Media Content Analysis: Natural Language Processing and Beyond (pp. 171-195). World Scientific Publishing Co. Pte Ltd. https://doi.org/10.1142/9789813223615_0013

Build emotion lexicon from microblogs by combining effects of seed words and emoticons in a heterogeneous graph. / Song, Kaisong; Feng, Shi; Gao, Wei; Wang, Daling; Chen, Ling; Zhang, Chengqi.

Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, 2017. p. 171-195.

Research output: Chapter in Book/Report/Conference proceedingChapter

Song, K, Feng, S, Gao, W, Wang, D, Chen, L & Zhang, C 2017, Build emotion lexicon from microblogs by combining effects of seed words and emoticons in a heterogeneous graph. in Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, pp. 171-195. https://doi.org/10.1142/9789813223615_0013
Song K, Feng S, Gao W, Wang D, Chen L, Zhang C. Build emotion lexicon from microblogs by combining effects of seed words and emoticons in a heterogeneous graph. In Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd. 2017. p. 171-195 https://doi.org/10.1142/9789813223615_0013
Song, Kaisong ; Feng, Shi ; Gao, Wei ; Wang, Daling ; Chen, Ling ; Zhang, Chengqi. / Build emotion lexicon from microblogs by combining effects of seed words and emoticons in a heterogeneous graph. Social Media Content Analysis: Natural Language Processing and Beyond. World Scientific Publishing Co. Pte Ltd, 2017. pp. 171-195
@inbook{b5a1da7b61aa48d58481780be804588c,
title = "Build emotion lexicon from microblogs by combining effects of seed words and emoticons in a heterogeneous graph",
abstract = "As an indispensable resource for emotion analysis, emotion lexicons have attracted increasing attention in recent years. Most existing methods focus on capturing the single emotional effect of words rather than the emotion distributions which are helpful to model multiple complex emotions in a subjective text. Meanwhile, automatic lexicon building methods are overly dependent on seed words but neglect the effect of emoticons which are natural graphical labels of fine-grained emotion. In this chapter, we describe a novel emotion lexicon building framework that leverages both seed words and emoticons simultaneously to capture emotion distributions of candidate words more accurately. Our method overcomes the weakness of existing methods by combining the effects of both seed words and emoticons in a unified three-layer heterogeneous graph, in which a multi-label random walk (MLRW) algorithm is performed to strengthen the emotion distribution estimation. Experimental results on real-world data reveal that our constructed emotion lexicon achieves promising results for emotion classification compared to the state-of-the-art lexicons.",
author = "Kaisong Song and Shi Feng and Wei Gao and Daling Wang and Ling Chen and Chengqi Zhang",
year = "2017",
month = "1",
day = "1",
doi = "10.1142/9789813223615_0013",
language = "English",
isbn = "9789813223608",
pages = "171--195",
booktitle = "Social Media Content Analysis",
publisher = "World Scientific Publishing Co. Pte Ltd",
address = "Singapore",

}

TY - CHAP

T1 - Build emotion lexicon from microblogs by combining effects of seed words and emoticons in a heterogeneous graph

AU - Song, Kaisong

AU - Feng, Shi

AU - Gao, Wei

AU - Wang, Daling

AU - Chen, Ling

AU - Zhang, Chengqi

PY - 2017/1/1

Y1 - 2017/1/1

N2 - As an indispensable resource for emotion analysis, emotion lexicons have attracted increasing attention in recent years. Most existing methods focus on capturing the single emotional effect of words rather than the emotion distributions which are helpful to model multiple complex emotions in a subjective text. Meanwhile, automatic lexicon building methods are overly dependent on seed words but neglect the effect of emoticons which are natural graphical labels of fine-grained emotion. In this chapter, we describe a novel emotion lexicon building framework that leverages both seed words and emoticons simultaneously to capture emotion distributions of candidate words more accurately. Our method overcomes the weakness of existing methods by combining the effects of both seed words and emoticons in a unified three-layer heterogeneous graph, in which a multi-label random walk (MLRW) algorithm is performed to strengthen the emotion distribution estimation. Experimental results on real-world data reveal that our constructed emotion lexicon achieves promising results for emotion classification compared to the state-of-the-art lexicons.

AB - As an indispensable resource for emotion analysis, emotion lexicons have attracted increasing attention in recent years. Most existing methods focus on capturing the single emotional effect of words rather than the emotion distributions which are helpful to model multiple complex emotions in a subjective text. Meanwhile, automatic lexicon building methods are overly dependent on seed words but neglect the effect of emoticons which are natural graphical labels of fine-grained emotion. In this chapter, we describe a novel emotion lexicon building framework that leverages both seed words and emoticons simultaneously to capture emotion distributions of candidate words more accurately. Our method overcomes the weakness of existing methods by combining the effects of both seed words and emoticons in a unified three-layer heterogeneous graph, in which a multi-label random walk (MLRW) algorithm is performed to strengthen the emotion distribution estimation. Experimental results on real-world data reveal that our constructed emotion lexicon achieves promising results for emotion classification compared to the state-of-the-art lexicons.

UR - http://www.scopus.com/inward/record.url?scp=85041570659&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041570659&partnerID=8YFLogxK

U2 - 10.1142/9789813223615_0013

DO - 10.1142/9789813223615_0013

M3 - Chapter

SN - 9789813223608

SP - 171

EP - 195

BT - Social Media Content Analysis

PB - World Scientific Publishing Co. Pte Ltd

ER -