Analyzing Stance and Topic of E-Cigarette Conversations on Twitter: Case Study in Indonesia

Cristin Purnama Sari Kaunang, Fitria Amastini, Rahmad Mahendra

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)

Abstract

To control the use of e-cigarette, Indonesia plan to establish a regulation that embodies all the concerns, sentiments, and opinions of public This study aims to identify public opinions in social media Twitter by classifying tweets into group in favor or against e-cigarette and explore dominant topics of each group. This research obtained 15,373 tweets between June 2019 - May 2020 that is classified into 4 labels: Against, Favor, Neutral, and Irrelevant. The best model was selected with specification: 3 features (Count, Unigram, and Bigram), Logistic Regression algorithm, and three-stage classification pipeline (\mathrm{F}1-\text{score}=0.807). As for topic modelling, corpus Against and Favor are used to retrieve dominant topics. We chose Non-negative Matrix Factorization algorithm with \mathrm{k}=6 and achieve high coherence scores, which are 0.962004 for corpus Against and 0.999736 for corpus Favor.

Original languageEnglish
Title of host publication2021 IEEE 11th Annual Computing and Communication Workshop and Conference, CCWC 2021
EditorsRajashree Paul
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages304-310
Number of pages7
ISBN (Electronic)9780738143941
DOIs
Publication statusPublished - 27 Jan 2021
Event11th IEEE Annual Computing and Communication Workshop and Conference, CCWC 2021 - Virtual, Las Vegas, United States
Duration: 27 Jan 202130 Jan 2021

Publication series

Name2021 IEEE 11th Annual Computing and Communication Workshop and Conference, CCWC 2021

Conference

Conference11th IEEE Annual Computing and Communication Workshop and Conference, CCWC 2021
Country/TerritoryUnited States
CityVirtual, Las Vegas
Period27/01/2130/01/21

Keywords

  • classification method
  • e-cigarettes
  • stance detection
  • text mining
  • topic modelling
  • vape

Fingerprint

Dive into the research topics of 'Analyzing Stance and Topic of E-Cigarette Conversations on Twitter: Case Study in Indonesia'. Together they form a unique fingerprint.

Cite this