Multi-view learning for emotion detection in code-switching texts

Yat Mei Lee; Zhongqing Wang

doi:10.1109/IALP.2015.7451539

Multi-view learning for emotion detection in code-switching texts

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

15 Citations (Scopus)

Abstract

Previous researches have placed emphasis on analyzing emotions in monolingual text, neglecting the fact that emotions are often found in bilingual or code-switching posts in social media. Traditional methods for the identification or classification of emotion fail to accommodate the code-switching content. To address this challenge, in this paper, we propose a multi-view learning framework to learn and detect the emotions through both monolingual and bilingual views. In particular, the monolingual views are extracted from the monolingual text separately, and the bilingual view is constructed with both monolingual and translated text collectively. Empirical studies demonstrate the effectiveness of our proposed approach in detecting emotions in code-switching texts.

Original language	English
Title of host publication	Proceedings of 2015 International Conference on Asian Language Processing, IALP 2015
Publisher	IEEE
Pages	90-93
Number of pages	4
ISBN (Electronic)	9781467395953
DOIs	https://doi.org/10.1109/IALP.2015.7451539
Publication status	Published - 12 Apr 2016
Event	International Conference on Asian Language Processing, IALP 2015 - Suzhou, China Duration: 24 Oct 2015 → 25 Oct 2015

Conference

Conference	International Conference on Asian Language Processing, IALP 2015
Country/Territory	China
City	Suzhou
Period	24/10/15 → 25/10/15

Keywords

code-switching
emotion analysis
multi-view learning

ASJC Scopus subject areas

Linguistics and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
Signal Processing

More information

10.1109/IALP.2015.7451539

http://hdl.handle.net/10397/76642

Cite this

@inproceedings{ce1efbe1ce0b483f83490351e0c381b3,

title = "Multi-view learning for emotion detection in code-switching texts",

abstract = "Previous researches have placed emphasis on analyzing emotions in monolingual text, neglecting the fact that emotions are often found in bilingual or code-switching posts in social media. Traditional methods for the identification or classification of emotion fail to accommodate the code-switching content. To address this challenge, in this paper, we propose a multi-view learning framework to learn and detect the emotions through both monolingual and bilingual views. In particular, the monolingual views are extracted from the monolingual text separately, and the bilingual view is constructed with both monolingual and translated text collectively. Empirical studies demonstrate the effectiveness of our proposed approach in detecting emotions in code-switching texts.",

keywords = "code-switching, emotion analysis, multi-view learning",

author = "Lee, {Yat Mei} and Zhongqing Wang",

year = "2016",

month = apr,

day = "12",

doi = "10.1109/IALP.2015.7451539",

language = "English",

pages = "90--93",

booktitle = "Proceedings of 2015 International Conference on Asian Language Processing, IALP 2015",

publisher = "IEEE",

address = "United States",

note = "International Conference on Asian Language Processing, IALP 2015 ; Conference date: 24-10-2015 Through 25-10-2015",

}

TY - GEN

T1 - Multi-view learning for emotion detection in code-switching texts

AU - Lee, Yat Mei

AU - Wang, Zhongqing

PY - 2016/4/12

Y1 - 2016/4/12

N2 - Previous researches have placed emphasis on analyzing emotions in monolingual text, neglecting the fact that emotions are often found in bilingual or code-switching posts in social media. Traditional methods for the identification or classification of emotion fail to accommodate the code-switching content. To address this challenge, in this paper, we propose a multi-view learning framework to learn and detect the emotions through both monolingual and bilingual views. In particular, the monolingual views are extracted from the monolingual text separately, and the bilingual view is constructed with both monolingual and translated text collectively. Empirical studies demonstrate the effectiveness of our proposed approach in detecting emotions in code-switching texts.

AB - Previous researches have placed emphasis on analyzing emotions in monolingual text, neglecting the fact that emotions are often found in bilingual or code-switching posts in social media. Traditional methods for the identification or classification of emotion fail to accommodate the code-switching content. To address this challenge, in this paper, we propose a multi-view learning framework to learn and detect the emotions through both monolingual and bilingual views. In particular, the monolingual views are extracted from the monolingual text separately, and the bilingual view is constructed with both monolingual and translated text collectively. Empirical studies demonstrate the effectiveness of our proposed approach in detecting emotions in code-switching texts.

KW - code-switching

KW - emotion analysis

KW - multi-view learning

UR - http://www.scopus.com/inward/record.url?scp=84970006328&partnerID=8YFLogxK

U2 - 10.1109/IALP.2015.7451539

DO - 10.1109/IALP.2015.7451539

M3 - Conference article published in proceeding or book

SP - 90

EP - 93

BT - Proceedings of 2015 International Conference on Asian Language Processing, IALP 2015

PB - IEEE

T2 - International Conference on Asian Language Processing, IALP 2015

Y2 - 24 October 2015 through 25 October 2015

ER -

Multi-view learning for emotion detection in code-switching texts

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this