Creating and Evaluating Resources for Sentiment Analysis in the Low-resource Language: Sindhi

Wazir Ali; Naveed Ali; Yong Dai; Jay Kumar; Saifullah Tumrani; Zenglin Xu

Creating and Evaluating Resources for Sentiment Analysis in the Low-resource Language: Sindhi

Wazir Ali
, Naveed Ali
, Yong Dai
, Jay Kumar
, Saifullah Tumrani
, Zenglin Xu

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

10 Scopus citations

Abstract

In this paper, we develop Sindhi subjective lexicon using a merger of existing English resources: NRC lexicon, list of opinion words, SentiWordNet, Sindhi-English bilingual dictionary, and collection of Sindhi modifiers. The positive or negative sentiment score is assigned to each Sindhi opinion word. Afterwards, we determine the coverage of the proposed lexicon with subjectivity analysis. Moreover, we crawl multi-domain tweet corpus of news, sports, and finance. The crawled corpus is annotated by experienced annotators using the Doccano text annotation tool. The sentiment annotated corpus is evaluated by employing support vector machine (SVM), recurrent neural network (RNN) variants, and convolutional neural network (CNN).

Original language	English
Title of host publication	WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop
Editors	Orphee De Clercq, Alexandra Balahur, Joao Sedoc, Valentin Barriere, Shabnam Tafreshi, Sven Buechel, Veronique Hoste
Publisher	Association for Computational Linguistics (ACL)
Pages	188-194
Number of pages	7
ISBN (Electronic)	9781954085183
State	Published - 2021
Externally published	Yes
Event	11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2021 - Virtual, Online Duration: 19 Apr 2021 → …

Publication series

Name	WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop

Conference

Conference	11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2021
City	Virtual, Online
Period	19/04/21 → …

Bibliographical note

Publisher Copyright:
© 2021 Association for Computational Linguistics.

ASJC Scopus subject areas

Computational Theory and Mathematics
Computer Networks and Communications
Information Systems
Communication

Cite this

Ali, W., Ali, N., Dai, Y., Kumar, J., Tumrani, S., & Xu, Z. (2021). Creating and Evaluating Resources for Sentiment Analysis in the Low-resource Language: Sindhi. In O. De Clercq, A. Balahur, J. Sedoc, V. Barriere, S. Tafreshi, S. Buechel, & V. Hoste (Eds.), WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop (pp. 188-194). (WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop). Association for Computational Linguistics (ACL).

Ali, Wazir ; Ali, Naveed ; Dai, Yong et al. / Creating and Evaluating Resources for Sentiment Analysis in the Low-resource Language : Sindhi. WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop. editor / Orphee De Clercq ; Alexandra Balahur ; Joao Sedoc ; Valentin Barriere ; Shabnam Tafreshi ; Sven Buechel ; Veronique Hoste. Association for Computational Linguistics (ACL), 2021. pp. 188-194 (WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop).

@inproceedings{aa785d73a33e40f18c0dac19b3b7bb6c,

title = "Creating and Evaluating Resources for Sentiment Analysis in the Low-resource Language: Sindhi",

abstract = "In this paper, we develop Sindhi subjective lexicon using a merger of existing English resources: NRC lexicon, list of opinion words, SentiWordNet, Sindhi-English bilingual dictionary, and collection of Sindhi modifiers. The positive or negative sentiment score is assigned to each Sindhi opinion word. Afterwards, we determine the coverage of the proposed lexicon with subjectivity analysis. Moreover, we crawl multi-domain tweet corpus of news, sports, and finance. The crawled corpus is annotated by experienced annotators using the Doccano text annotation tool. The sentiment annotated corpus is evaluated by employing support vector machine (SVM), recurrent neural network (RNN) variants, and convolutional neural network (CNN).",

author = "Wazir Ali and Naveed Ali and Yong Dai and Jay Kumar and Saifullah Tumrani and Zenglin Xu",

note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics.; 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2021 ; Conference date: 19-04-2021",

year = "2021",

language = "English",

series = "WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop",

publisher = "Association for Computational Linguistics (ACL)",

pages = "188--194",

editor = "\{De Clercq\}, Orphee and Alexandra Balahur and Joao Sedoc and Valentin Barriere and Shabnam Tafreshi and Sven Buechel and Veronique Hoste",

booktitle = "WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop",

address = "United States",

}

Ali, W, Ali, N, Dai, Y, Kumar, J, Tumrani, S & Xu, Z 2021, Creating and Evaluating Resources for Sentiment Analysis in the Low-resource Language: Sindhi. in O De Clercq, A Balahur, J Sedoc, V Barriere, S Tafreshi, S Buechel & V Hoste (eds), WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop. WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop, Association for Computational Linguistics (ACL), pp. 188-194, 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2021, Virtual, Online, 19/04/21.

Creating and Evaluating Resources for Sentiment Analysis in the Low-resource Language: Sindhi. / Ali, Wazir; Ali, Naveed; Dai, Yong et al.
WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop. ed. / Orphee De Clercq; Alexandra Balahur; Joao Sedoc; Valentin Barriere; Shabnam Tafreshi; Sven Buechel; Veronique Hoste. Association for Computational Linguistics (ACL), 2021. p. 188-194 (WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop).

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

TY - GEN

T1 - Creating and Evaluating Resources for Sentiment Analysis in the Low-resource Language

T2 - 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2021

AU - Ali, Wazir

AU - Ali, Naveed

AU - Dai, Yong

AU - Kumar, Jay

AU - Tumrani, Saifullah

AU - Xu, Zenglin

PY - 2021

Y1 - 2021

N2 - In this paper, we develop Sindhi subjective lexicon using a merger of existing English resources: NRC lexicon, list of opinion words, SentiWordNet, Sindhi-English bilingual dictionary, and collection of Sindhi modifiers. The positive or negative sentiment score is assigned to each Sindhi opinion word. Afterwards, we determine the coverage of the proposed lexicon with subjectivity analysis. Moreover, we crawl multi-domain tweet corpus of news, sports, and finance. The crawled corpus is annotated by experienced annotators using the Doccano text annotation tool. The sentiment annotated corpus is evaluated by employing support vector machine (SVM), recurrent neural network (RNN) variants, and convolutional neural network (CNN).

AB - In this paper, we develop Sindhi subjective lexicon using a merger of existing English resources: NRC lexicon, list of opinion words, SentiWordNet, Sindhi-English bilingual dictionary, and collection of Sindhi modifiers. The positive or negative sentiment score is assigned to each Sindhi opinion word. Afterwards, we determine the coverage of the proposed lexicon with subjectivity analysis. Moreover, we crawl multi-domain tweet corpus of news, sports, and finance. The crawled corpus is annotated by experienced annotators using the Doccano text annotation tool. The sentiment annotated corpus is evaluated by employing support vector machine (SVM), recurrent neural network (RNN) variants, and convolutional neural network (CNN).

UR - https://www.scopus.com/pages/publications/85120001996

M3 - Conference contribution

AN - SCOPUS:85120001996

T3 - WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop

SP - 188

EP - 194

BT - WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop

A2 - De Clercq, Orphee

A2 - Balahur, Alexandra

A2 - Sedoc, Joao

A2 - Barriere, Valentin

A2 - Tafreshi, Shabnam

A2 - Buechel, Sven

A2 - Hoste, Veronique

PB - Association for Computational Linguistics (ACL)

Y2 - 19 April 2021

ER -

Ali W, Ali N, Dai Y, Kumar J, Tumrani S, Xu Z. Creating and Evaluating Resources for Sentiment Analysis in the Low-resource Language: Sindhi. In De Clercq O, Balahur A, Sedoc J, Barriere V, Tafreshi S, Buechel S, Hoste V, editors, WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop. Association for Computational Linguistics (ACL). 2021. p. 188-194. (WASSA 2021 - Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the 11th Workshop).

Creating and Evaluating Resources for Sentiment Analysis in the Low-resource Language: Sindhi

Abstract

Publication series

Conference

Bibliographical note

ASJC Scopus subject areas

Fingerprint

Cite this