Accepted for/Published in: JMIR Infodemiology
Date Submitted: Apr 23, 2025
Date Accepted: Jan 15, 2026
Analyzing Mis/Disinformation: Understanding Swiss COVID-19 Narratives Through NLP Analysis
ABSTRACT
Background:
The COVID-19 pandemic has highlighted the challenges posed by the rapid spread of mis/disinformation, exacerbating societal polarization and institutional distrust. Understanding how mis/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 its framing within newspaper articles and social media interactions. The findings aim to inform policymakers and journalists/communicators on mitigating the societal impact of mis/disinformation through the promotion of a common understanding of the terms misinformation and disinformation.
Methods:
We analyzed two datasets using an NLP 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 mis/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 mis/disinformation across public discourse reflect broader societal tensions. Robust journalistic integrity in the media, and resilience strategies against mis/disinformation involving empowering publics through information literacy approaches are critical to bridging divides and reducing polarization.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.