TY - GEN
T1 - Demographic Analysis of Candidates Supporter in Twitter during Indonesian Presidential Election 2019
AU - Arafat, Thaufan Ardi
AU - Budi, Indra
AU - Mahendra, Rahmad
AU - Salehah, Dena Aurum
N1 - Funding Information:
We gratefully thank the Universitas Indonesia for the International Publication Grants (PUTI Q2) No. NKB-1475/UN2.RST/HKP.05.00/2020.
Publisher Copyright:
© 2020 IEEE.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2020/11/19
Y1 - 2020/11/19
N2 - In today's political world, the use of social media as a medium to convey political views and using it for campaign has become a very common thing. Social media can be used to express one's expression both in supporting a political party and someone who is running for politics. Twitter is one of the social media that is often used for campaign, this is because of Twitter's unformal and chronological feature. But Twitter also has weakness such as the absence of demographic information. Therefore, this study aims to find out the demographic patterns of supporter of each Indonesian Presidential candidate 2019 on Indonesian language Twitter. For searching the demographics, this study using text classification method and dictionary of names and genders. The dictionary comes from KPU permanent voter data. Demographic labels used in this study consist of male, female, generation Z, millennial generation, generation X+, outside Java and Java. To determine the political preference, this study uses the sentiment analysis method that is suitable for short sentences, namely the SentiStrength method. The results of this study indicate that most Twitter users who actively talk related to the politics of 2019 Presidential and Vice-Presidential elections are women with millennial age categories or 25-39 years old.
AB - In today's political world, the use of social media as a medium to convey political views and using it for campaign has become a very common thing. Social media can be used to express one's expression both in supporting a political party and someone who is running for politics. Twitter is one of the social media that is often used for campaign, this is because of Twitter's unformal and chronological feature. But Twitter also has weakness such as the absence of demographic information. Therefore, this study aims to find out the demographic patterns of supporter of each Indonesian Presidential candidate 2019 on Indonesian language Twitter. For searching the demographics, this study using text classification method and dictionary of names and genders. The dictionary comes from KPU permanent voter data. Demographic labels used in this study consist of male, female, generation Z, millennial generation, generation X+, outside Java and Java. To determine the political preference, this study uses the sentiment analysis method that is suitable for short sentences, namely the SentiStrength method. The results of this study indicate that most Twitter users who actively talk related to the politics of 2019 Presidential and Vice-Presidential elections are women with millennial age categories or 25-39 years old.
KW - demographic analysis
KW - sentiment analysis
KW - text classification
UR - http://www.scopus.com/inward/record.url?scp=85099786169&partnerID=8YFLogxK
U2 - 10.1109/ICISS50791.2020.9307598
DO - 10.1109/ICISS50791.2020.9307598
M3 - Conference contribution
AN - SCOPUS:85099786169
T3 - 7th International Conference on ICT for Smart Society: AIoT for Smart Society, ICISS 2020 - Proceeding
BT - 7th International Conference on ICT for Smart Society
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th International Conference on ICT for Smart Society, ICISS 2020
Y2 - 19 November 2020 through 20 November 2020
ER -