Cluster-Based BERTopic Modeling on Swedish COVID-19 Vaccine Posts

Dimitrios Kokkinakis, Mia Marie Hammarlin

Research output: Chapter in Book/Report/Conference proceedingPaper in conference proceedingpeer-review

Abstract

This paper explores the prevalent themes across multiple threads on the popular Swedish discussion forum Flashback. Among its diverse array of topics, the forum actively engages users in addressing and debating questions pertaining to COVID-19 vaccines and vaccination. Through distinguishing between positive and negative perspectives within posts across 14 relevant thread discussions, we employ BERTopic, a modular topic modeling framework, which utilizes pre-trained language models and applies clustering techniques to identify prevailing topics. This enables us to conduct a nuanced exploration of overarching themes, offering valuable insights into the multifaceted nature of the discussions regarding COVID-19 vaccines and vaccination in Sweden.

Original languageEnglish
Title of host publicationDigital Health and Informatics Innovations for Sustainable Health Care Systems - Proceedings of MIE 2024
EditorsJohn Mantas, Arie Hasman, George Demiris, Kaija Saranto, Michael Marschollek, Theodoros N. Arvanitis, Ivana Ognjanovic, Arriel Benis, Parisis Gallos, Emmanouil Zoulias, Elisavet Andrikopoulou
PublisherIOS Press
Pages1906-1910
Number of pages5
ISBN (Electronic)9781643685335
DOIs
Publication statusPublished - 2024 Aug
Event34th Medical Informatics Europe Conference, MIE 2024 - Athens, Greece
Duration: 2024 Aug 252024 Aug 29

Publication series

NameStudies in Health Technology and Informatics
Volume316
ISSN (Print)0926-9630
ISSN (Electronic)1879-8365

Conference

Conference34th Medical Informatics Europe Conference, MIE 2024
Country/TerritoryGreece
CityAthens
Period2024/08/252024/08/29

Subject classification (UKÄ)

  • Natural Language Processing

Free keywords

  • BERTopic
  • Swedish dataset
  • topic modeling
  • vaccination
  • vaccine

Fingerprint

Dive into the research topics of 'Cluster-Based BERTopic Modeling on Swedish COVID-19 Vaccine Posts'. Together they form a unique fingerprint.

Cite this