IASL valence-Arousal analysis system at IALP 2016 shared task: Dimensional sentiment analysis for Chinese words

Yu Lun Hsieh; Chen Ann Wang; Ying Wei Wu; Yung Chun Chang; Wen Lian Hsu

doi:10.1109/IALP.2016.7875990

IASL valence-Arousal analysis system at IALP 2016 shared task: Dimensional sentiment analysis for Chinese words

Yu Lun Hsieh, Chen Ann Wang, Ying Wei Wu, Yung Chun Chang, Wen Lian Hsu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Sentiment lexicons with valence-Arousal ratings are useful resources for the development of dimensional sentiment applications. In order to solve the significant lack of Chinese valence and arousal lexicons, the objective of the DSAW is to automatically acquire the valence-Arousal ratings of Chinese affective words. In this task, we develop a novel approach that integrate word embeddings into a graph-based model with K-Nearest Neighbor to identify both valence and arousal dimensions. We also propose to use character embeddings to represent unseen words, which is a major challenge in collecting large corpora. The evaluation results demonstrate that our system is effective in dimensional sentiment analysis for Chinese words with 0.847 and 1.281 mean absolute error (MAE) for valence and arousal respectively.

Original language	English
Title of host publication	Proceedings of the 2016 International Conference on Asian Language Processing, IALP 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	297-299
Number of pages	3
ISBN (Electronic)	9781509009213
DOIs	https://doi.org/10.1109/IALP.2016.7875990
Publication status	Published - Mar 10 2017
Externally published	Yes
Event	20th International Conference on Asian Language Processing, IALP 2016 - Tainan, Taiwan Duration: Nov 21 2016 → Nov 23 2016

Conference

Conference	20th International Conference on Asian Language Processing, IALP 2016
Country/Territory	Taiwan
City	Tainan
Period	11/21/16 → 11/23/16

ASJC Scopus subject areas

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

Access to Document

10.1109/IALP.2016.7875990

Cite this

Hsieh, Y. L., Wang, C. A., Wu, Y. W., Chang, Y. C., & Hsu, W. L. (2017). IASL valence-Arousal analysis system at IALP 2016 shared task: Dimensional sentiment analysis for Chinese words. In Proceedings of the 2016 International Conference on Asian Language Processing, IALP 2016 (pp. 297-299). Article 7875990 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IALP.2016.7875990

IASL valence-Arousal analysis system at IALP 2016 shared task: Dimensional sentiment analysis for Chinese words. / Hsieh, Yu Lun; Wang, Chen Ann; Wu, Ying Wei et al.
Proceedings of the 2016 International Conference on Asian Language Processing, IALP 2016. Institute of Electrical and Electronics Engineers Inc., 2017. p. 297-299 7875990.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Hsieh, YL, Wang, CA, Wu, YW, Chang, YC & Hsu, WL 2017, IASL valence-Arousal analysis system at IALP 2016 shared task: Dimensional sentiment analysis for Chinese words. in Proceedings of the 2016 International Conference on Asian Language Processing, IALP 2016., 7875990, Institute of Electrical and Electronics Engineers Inc., pp. 297-299, 20th International Conference on Asian Language Processing, IALP 2016, Tainan, Taiwan, 11/21/16. https://doi.org/10.1109/IALP.2016.7875990

@inproceedings{007963b6aced4d3ba5f099e5504d962a,

title = "IASL valence-Arousal analysis system at IALP 2016 shared task: Dimensional sentiment analysis for Chinese words",

abstract = "Sentiment lexicons with valence-Arousal ratings are useful resources for the development of dimensional sentiment applications. In order to solve the significant lack of Chinese valence and arousal lexicons, the objective of the DSAW is to automatically acquire the valence-Arousal ratings of Chinese affective words. In this task, we develop a novel approach that integrate word embeddings into a graph-based model with K-Nearest Neighbor to identify both valence and arousal dimensions. We also propose to use character embeddings to represent unseen words, which is a major challenge in collecting large corpora. The evaluation results demonstrate that our system is effective in dimensional sentiment analysis for Chinese words with 0.847 and 1.281 mean absolute error (MAE) for valence and arousal respectively.",

author = "Hsieh, {Yu Lun} and Wang, {Chen Ann} and Wu, {Ying Wei} and Chang, {Yung Chun} and Hsu, {Wen Lian}",

year = "2017",

month = mar,

day = "10",

doi = "10.1109/IALP.2016.7875990",

language = "English",

pages = "297--299",

booktitle = "Proceedings of the 2016 International Conference on Asian Language Processing, IALP 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "20th International Conference on Asian Language Processing, IALP 2016 ; Conference date: 21-11-2016 Through 23-11-2016",

}

TY - GEN

T1 - IASL valence-Arousal analysis system at IALP 2016 shared task

T2 - 20th International Conference on Asian Language Processing, IALP 2016

AU - Hsieh, Yu Lun

AU - Wang, Chen Ann

AU - Wu, Ying Wei

AU - Chang, Yung Chun

AU - Hsu, Wen Lian

PY - 2017/3/10

Y1 - 2017/3/10

N2 - Sentiment lexicons with valence-Arousal ratings are useful resources for the development of dimensional sentiment applications. In order to solve the significant lack of Chinese valence and arousal lexicons, the objective of the DSAW is to automatically acquire the valence-Arousal ratings of Chinese affective words. In this task, we develop a novel approach that integrate word embeddings into a graph-based model with K-Nearest Neighbor to identify both valence and arousal dimensions. We also propose to use character embeddings to represent unseen words, which is a major challenge in collecting large corpora. The evaluation results demonstrate that our system is effective in dimensional sentiment analysis for Chinese words with 0.847 and 1.281 mean absolute error (MAE) for valence and arousal respectively.

AB - Sentiment lexicons with valence-Arousal ratings are useful resources for the development of dimensional sentiment applications. In order to solve the significant lack of Chinese valence and arousal lexicons, the objective of the DSAW is to automatically acquire the valence-Arousal ratings of Chinese affective words. In this task, we develop a novel approach that integrate word embeddings into a graph-based model with K-Nearest Neighbor to identify both valence and arousal dimensions. We also propose to use character embeddings to represent unseen words, which is a major challenge in collecting large corpora. The evaluation results demonstrate that our system is effective in dimensional sentiment analysis for Chinese words with 0.847 and 1.281 mean absolute error (MAE) for valence and arousal respectively.

UR - http://www.scopus.com/inward/record.url?scp=85017216135&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017216135&partnerID=8YFLogxK

U2 - 10.1109/IALP.2016.7875990

DO - 10.1109/IALP.2016.7875990

M3 - Conference contribution

AN - SCOPUS:85017216135

SP - 297

EP - 299

BT - Proceedings of the 2016 International Conference on Asian Language Processing, IALP 2016

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 21 November 2016 through 23 November 2016

ER -

IASL valence-Arousal analysis system at IALP 2016 shared task: Dimensional sentiment analysis for Chinese words

Abstract

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this