EUVIMEDDescoperă EUVIMED
Open access

Analyzing Misinformation and Disinformation: Understanding Swiss COVID-19 Narratives Through Natural Language Processing Analysis

Federico Germani iD, Giovanni Spitale iD, Franc Fritschi iD, Sonja Merten iD, Nikola Biller-Andorno iD

JMIR Infodemiology · 2026-03-30 · 6 · e76441-e76441

DOI: 10.2196/76441 ↗

At a glance

Journal article in JMIR Infodemiology, published online on 2026-03-30. Written by Federico Germani and 4 co-authors. Institution: Institute of Biomedical Ethics and History of Medicine, University of Zurich, Winterthurerstrasse 30, Zürich, 8006, Switzerland, 41 44 634 40 80. Major MEDLINE topics: COVID-19, Natural Language Processing, Communication, Disinformation. 39 references. The full text is freely available in PubMed Central.

RezumatSubjectsDate bibliograficeCiteRelated studies

Abstract (original language)

Background

The COVID-19 pandemic has highlighted the challenges posed by the rapid spread of misinformation and disinformation, exacerbating societal polarization and institutional distrust. Understanding how misinformation and disinformation is understood and framed in public discourse is essential to developing strategies for building societal resilience and promoting informed decision-making during crises.

Objective

This study explores the use of the terms misinformation and disinformation across Swiss public discourse during the COVID-19 pandemic, examining their framing within newspaper articles and social media interactions. The findings aim to inform policymakers and journalists or communicators on mitigating the societal impact of misinformation and disinformation through the promotion of a common understanding of the terms misinformation and disinformation.

Methods

We analyzed 2 datasets using a natural language processing pipeline, including lemmatization, co-occurrence analysis, and semantic network mapping: media articles retrieved via Factiva and social media posts collected via CrowdTangle.

Results

The framing of misinformation and disinformation varied significantly across the datasets. News media highlighted its role in shaping public sentiment, often discussing the tension between journalistic integrity and the amplification of falsehoods. Social media exhibited polarized narratives, with discussions centered on conspiracy theories, distrust in institutions, and grassroots mobilization.

Conclusions

Diverging narratives on the very concepts of misinformation and disinformation across public discourse reflect broader societal tensions. Robust journalistic integrity in the media and resilience strategies against misinformation and disinformation involving empowering publics through information literacy approaches are critical to bridging divides and reducing polarization.

Subjects

MeSH terms (MEDLINE)

COVID-19Natural Language ProcessingCommunicationDisinformationSwitzerlandHumansSocial MediaPandemicsSARS-CoV-2Newspapers as Topic

Author keywords

COVID-19Switzerlanddisinformationmisinformationnatural language processingpublic discourse

Authors and institutions

  • Institute of Biomedical Ethics and History of Medicine, University of Zurich, Winterthurerstrasse 30, Zürich, 8006, Switzerland, 41 44 634 40 80.
  • Swiss Tropical and Public Health Institute, University of Basel, Basel, Switzerland.

ORCID profiles: Federico Germani, Giovanni Spitale, Franc Fritschi, Sonja Merten, Nikola Biller-Andorno

Cite

APA

Germani, F., Spitale, G., Fritschi, F., Merten, S., & Biller-Andorno, N. (2026). Analyzing Misinformation and Disinformation: Understanding Swiss COVID-19 Narratives Through Natural Language Processing Analysis. JMIR Infodemiology, 6, e76441-e76441. https://doi.org/10.2196/76441

Vancouver

Germani F, Spitale G, Fritschi F, Merten S, Biller-Andorno N. Analyzing Misinformation and Disinformation: Understanding Swiss COVID-19 Narratives Through Natural Language Processing Analysis. JMIR Infodemiology. 2026;6:e76441-e76441. doi:10.2196/76441

BibTeX
@article{Germani2026,
  author = {Germani, Federico and Spitale, Giovanni and Fritschi, Franc and Merten, Sonja and Biller-Andorno, Nikola},
  title = {Analyzing Misinformation and Disinformation: Understanding Swiss COVID-19 Narratives Through Natural Language Processing Analysis},
  journal = {JMIR Infodemiology},
  year = {2026},
  volume = {6},
  pages = {e76441--e76441},
  doi = {10.2196/76441}
}
Start for free →