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 proceedingConference contribution

14 Citations (Scopus)

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 paper, we propose 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 publicationHT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media
PublisherAssociation for Computing Machinery, Inc
Pages283-292
Number of pages10
ISBN (Electronic)9781450333955
DOIs
Publication statusPublished - 24 Aug 2015
Event26th ACM Conference on Hypertext and Social Media, HT 2015 - Guzelyurt, Cyprus
Duration: 1 Sep 20154 Sep 2015

Other

Other26th ACM Conference on Hypertext and Social Media, HT 2015
CountryCyprus
CityGuzelyurt
Period1/9/154/9/15

Fingerprint

Seed
Labels

Keywords

  • Emoticon
  • Emotion lexicon
  • Heterogeneous graph
  • Microblogs
  • Seed word

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction

Cite this

Song, K., Feng, S., Gao, W., Wang, D., Chen, L., & Zhang, C. (2015). Build emotion lexicon from microblogs by combining effects of seed words and emoticons in a heterogeneous graph. In HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media (pp. 283-292). Association for Computing Machinery, Inc. https://doi.org/10.1145/2700171.2791035

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.

HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc, 2015. p. 283-292.

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

Song, K, Feng, S, Gao, W, Wang, D, Chen, L & Zhang, C 2015, Build emotion lexicon from microblogs by combining effects of seed words and emoticons in a heterogeneous graph. in HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc, pp. 283-292, 26th ACM Conference on Hypertext and Social Media, HT 2015, Guzelyurt, Cyprus, 1/9/15. https://doi.org/10.1145/2700171.2791035
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 HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc. 2015. p. 283-292 https://doi.org/10.1145/2700171.2791035
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. HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc, 2015. pp. 283-292
@inproceedings{ab7cd9070cd547258b87f24a38ccf4a7,
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 paper, we propose 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.",
keywords = "Emoticon, Emotion lexicon, Heterogeneous graph, Microblogs, Seed word",
author = "Kaisong Song and Shi Feng and Wei Gao and Daling Wang and Ling Chen and Chengqi Zhang",
year = "2015",
month = "8",
day = "24",
doi = "10.1145/2700171.2791035",
language = "English",
pages = "283--292",
booktitle = "HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media",
publisher = "Association for Computing Machinery, Inc",

}

TY - GEN

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 - 2015/8/24

Y1 - 2015/8/24

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 paper, we propose 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 paper, we propose 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.

KW - Emoticon

KW - Emotion lexicon

KW - Heterogeneous graph

KW - Microblogs

KW - Seed word

UR - http://www.scopus.com/inward/record.url?scp=84956997536&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84956997536&partnerID=8YFLogxK

U2 - 10.1145/2700171.2791035

DO - 10.1145/2700171.2791035

M3 - Conference contribution

AN - SCOPUS:84956997536

SP - 283

EP - 292

BT - HT 2015 - Proceedings of the 26th ACM Conference on Hypertext and Social Media

PB - Association for Computing Machinery, Inc

ER -