Joint learning on sentiment and emotion classification

Wei Gao; Shoushan Li; Yat Mei Lee; Guodong Zhou; Chu-ren Huang

doi:10.1145/2505515.2507830

Joint learning on sentiment and emotion classification

Wei Gao, Shoushan Li, Yat Mei Lee, Guodong Zhou, Chu-ren Huang

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

42 Citations (Scopus)

Abstract

Sentiment and emotion classification have been popularly but separately studied in natural language processing. In this paper, we address joint learning on sentiment and emotion classification where both the labeled data for sentiment and emotion classification are available. The objective of this joint-learning is to benefit the two tasks from each other for improving their performances. Specifically, an extra data set that is annotated with both sentiment and emotion labels are employed to estimate the transformation probability between the two kinds of labels. Furthermore, the transformation probability is leveraged to transfer the classification labels to benefit the two tasks from each other. Empirical studies demonstrate the effectiveness of our approach for the novel joint learning task.

Original language	English
Title of host publication	CIKM 2013 - Proceedings of the 22nd ACM International Conference on Information and Knowledge Management
Pages	1505-1508
Number of pages	4
DOIs	https://doi.org/10.1145/2505515.2507830
Publication status	Published - 11 Dec 2013
Event	22nd ACM International Conference on Information and Knowledge Management, CIKM 2013 - San Francisco, CA, United States Duration: 27 Oct 2013 → 1 Nov 2013

Conference

Conference	22nd ACM International Conference on Information and Knowledge Management, CIKM 2013
Country/Territory	United States
City	San Francisco, CA
Period	27/10/13 → 1/11/13

Keywords

Emotion classification
Joint learning
Sentiment classification

ASJC Scopus subject areas

General Decision Sciences
General Business,Management and Accounting

More information

10.1145/2505515.2507830

Cite this

@inproceedings{d6a5f392873144e49a80645d2ceb45e2,

title = "Joint learning on sentiment and emotion classification",

abstract = "Sentiment and emotion classification have been popularly but separately studied in natural language processing. In this paper, we address joint learning on sentiment and emotion classification where both the labeled data for sentiment and emotion classification are available. The objective of this joint-learning is to benefit the two tasks from each other for improving their performances. Specifically, an extra data set that is annotated with both sentiment and emotion labels are employed to estimate the transformation probability between the two kinds of labels. Furthermore, the transformation probability is leveraged to transfer the classification labels to benefit the two tasks from each other. Empirical studies demonstrate the effectiveness of our approach for the novel joint learning task.",

keywords = "Emotion classification, Joint learning, Sentiment classification",

author = "Wei Gao and Shoushan Li and Lee, {Yat Mei} and Guodong Zhou and Chu-ren Huang",

year = "2013",

month = dec,

day = "11",

doi = "10.1145/2505515.2507830",

language = "English",

isbn = "9781450322638",

pages = "1505--1508",

booktitle = "CIKM 2013 - Proceedings of the 22nd ACM International Conference on Information and Knowledge Management",

note = "22nd ACM International Conference on Information and Knowledge Management, CIKM 2013 ; Conference date: 27-10-2013 Through 01-11-2013",

}

Gao, W, Li, S, Lee, YM, Zhou, G & Huang, C 2013, Joint learning on sentiment and emotion classification. in CIKM 2013 - Proceedings of the 22nd ACM International Conference on Information and Knowledge Management. pp. 1505-1508, 22nd ACM International Conference on Information and Knowledge Management, CIKM 2013, San Francisco, CA, United States, 27/10/13. https://doi.org/10.1145/2505515.2507830

Joint learning on sentiment and emotion classification. / Gao, Wei; Li, Shoushan; Lee, Yat Mei et al.
CIKM 2013 - Proceedings of the 22nd ACM International Conference on Information and Knowledge Management. 2013. p. 1505-1508.

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

TY - GEN

T1 - Joint learning on sentiment and emotion classification

AU - Gao, Wei

AU - Li, Shoushan

AU - Lee, Yat Mei

AU - Zhou, Guodong

AU - Huang, Chu-ren

PY - 2013/12/11

Y1 - 2013/12/11

N2 - Sentiment and emotion classification have been popularly but separately studied in natural language processing. In this paper, we address joint learning on sentiment and emotion classification where both the labeled data for sentiment and emotion classification are available. The objective of this joint-learning is to benefit the two tasks from each other for improving their performances. Specifically, an extra data set that is annotated with both sentiment and emotion labels are employed to estimate the transformation probability between the two kinds of labels. Furthermore, the transformation probability is leveraged to transfer the classification labels to benefit the two tasks from each other. Empirical studies demonstrate the effectiveness of our approach for the novel joint learning task.

AB - Sentiment and emotion classification have been popularly but separately studied in natural language processing. In this paper, we address joint learning on sentiment and emotion classification where both the labeled data for sentiment and emotion classification are available. The objective of this joint-learning is to benefit the two tasks from each other for improving their performances. Specifically, an extra data set that is annotated with both sentiment and emotion labels are employed to estimate the transformation probability between the two kinds of labels. Furthermore, the transformation probability is leveraged to transfer the classification labels to benefit the two tasks from each other. Empirical studies demonstrate the effectiveness of our approach for the novel joint learning task.

KW - Emotion classification

KW - Joint learning

KW - Sentiment classification

UR - http://www.scopus.com/inward/record.url?scp=84889586455&partnerID=8YFLogxK

U2 - 10.1145/2505515.2507830

DO - 10.1145/2505515.2507830

M3 - Conference article published in proceeding or book

SN - 9781450322638

SP - 1505

EP - 1508

BT - CIKM 2013 - Proceedings of the 22nd ACM International Conference on Information and Knowledge Management

T2 - 22nd ACM International Conference on Information and Knowledge Management, CIKM 2013

Y2 - 27 October 2013 through 1 November 2013

ER -

Joint learning on sentiment and emotion classification

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this