Twitter stance detection towards Job Creation Bill

Arif Hamied Nababan; Rahmad Mahendra; Indra Budi

doi:10.1016/j.procs.2021.12.120

Twitter stance detection towards Job Creation Bill

Arif Hamied Nababan, Rahmad Mahendra, Indra Budi

Research output: Contribution to journal › Conference article › peer-review

6 Citations (Scopus)

Abstract

The formation of Job Creation Bill has raised the polemics in Indonesia. This study aims to identify the public's stance on the Job Creation Bill on Twitter social media. We collect tweets using keywords related to the Job Creation Bill and annotate nearly 10K tweets with a class label describing stance position. The experiments were conducted using the Naïve Bayes, Support Vector Machine, and Logistic Regression, with unigram and bigram features. The best performance in our experiment achieved by the Logistic Regression classifier using the unigram feature obtains a micro F-1 score of 71.8%.

Original language	English
Pages (from-to)	76-81
Number of pages	6
Journal	Procedia Computer Science
Volume	197
DOIs	https://doi.org/10.1016/j.procs.2021.12.120
Publication status	Published - 2021
Event	6th Information Systems International Conference, ISICO 2021 - Virtual, Online, Italy Duration: 7 Aug 2021 → 8 Aug 2021

Keywords

Job creation bill
Stance detection
Text classification
Twitter

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1016/j.procs.2021.12.120

Cite this

@article{5cc0b746077c4ee0b1c93244df6606c1,

title = "Twitter stance detection towards Job Creation Bill",

abstract = "The formation of Job Creation Bill has raised the polemics in Indonesia. This study aims to identify the public's stance on the Job Creation Bill on Twitter social media. We collect tweets using keywords related to the Job Creation Bill and annotate nearly 10K tweets with a class label describing stance position. The experiments were conducted using the Na{\"i}ve Bayes, Support Vector Machine, and Logistic Regression, with unigram and bigram features. The best performance in our experiment achieved by the Logistic Regression classifier using the unigram feature obtains a micro F-1 score of 71.8%.",

keywords = "Job creation bill, Stance detection, Text classification, Twitter",

author = "Nababan, {Arif Hamied} and Rahmad Mahendra and Indra Budi",

note = "Funding Information: We would like to thank Universitas Indonesia for their support through grant ?Publikasi Terindeks Internasional (PUTI) Q2: NKB-4060/UN2.RST/HKP.05.00/2020?. Publisher Copyright: {\textcopyright} 2021 The Authors. Published by Elsevier B.V.; 6th Information Systems International Conference, ISICO 2021 ; Conference date: 07-08-2021 Through 08-08-2021",

year = "2021",

doi = "10.1016/j.procs.2021.12.120",

language = "English",

volume = "197",

pages = "76--81",

journal = "Procedia Computer Science",

issn = "1877-0509",

publisher = "Elsevier B.V.",

}

TY - JOUR

T1 - Twitter stance detection towards Job Creation Bill

AU - Nababan, Arif Hamied

AU - Mahendra, Rahmad

AU - Budi, Indra

N1 - Funding Information: We would like to thank Universitas Indonesia for their support through grant ?Publikasi Terindeks Internasional (PUTI) Q2: NKB-4060/UN2.RST/HKP.05.00/2020?. Publisher Copyright: © 2021 The Authors. Published by Elsevier B.V.

PY - 2021

Y1 - 2021

N2 - The formation of Job Creation Bill has raised the polemics in Indonesia. This study aims to identify the public's stance on the Job Creation Bill on Twitter social media. We collect tweets using keywords related to the Job Creation Bill and annotate nearly 10K tweets with a class label describing stance position. The experiments were conducted using the Naïve Bayes, Support Vector Machine, and Logistic Regression, with unigram and bigram features. The best performance in our experiment achieved by the Logistic Regression classifier using the unigram feature obtains a micro F-1 score of 71.8%.

AB - The formation of Job Creation Bill has raised the polemics in Indonesia. This study aims to identify the public's stance on the Job Creation Bill on Twitter social media. We collect tweets using keywords related to the Job Creation Bill and annotate nearly 10K tweets with a class label describing stance position. The experiments were conducted using the Naïve Bayes, Support Vector Machine, and Logistic Regression, with unigram and bigram features. The best performance in our experiment achieved by the Logistic Regression classifier using the unigram feature obtains a micro F-1 score of 71.8%.

KW - Job creation bill

KW - Stance detection

KW - Text classification

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=85123782866&partnerID=8YFLogxK

U2 - 10.1016/j.procs.2021.12.120

DO - 10.1016/j.procs.2021.12.120

M3 - Conference article

AN - SCOPUS:85123782866

SN - 1877-0509

VL - 197

SP - 76

EP - 81

JO - Procedia Computer Science

JF - Procedia Computer Science

T2 - 6th Information Systems International Conference, ISICO 2021

Y2 - 7 August 2021 through 8 August 2021

ER -

Twitter stance detection towards Job Creation Bill

Abstract

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this