CoChat

The DOI matches its Crossref record; 54 of the 55 references it cites were found in a registry or an index.

Developing Misinformation Immunity: How to Reason-Check Fallacious News in a Human–Computer Interaction Environment

Open access

Abstract

To counter the fake news phenomenon, the scholarly community has attempted to debunk and prebunk disinformation. However, misinformation still constitutes a major challenge due to the variety of misleading techniques and their continuous updates which call for the exercise of critical thinking to build resilience. In this study we present two open access chatbots, the Fake News Immunity Chatbot and the Vaccinating News Chatbot, which combine Fallacy Theory and Human–Computer Interaction to inoculate citizens and communication gatekeepers against misinformation. These chatbots differ from existing tools both in function and form. First, they target misinformation and enhance the identification of fallacious arguments; and second, they are multiagent and leverage discourse theories of persuasion in their conversational design. After having described both their backend and their frontend design, we report on the evaluation of the user interface and impact on users’ critical thinking skills through a questionnaire, a crowdsourced survey, and a pilot qualitative experiment. The results shed light on the best practices to design user-friendly active inoculation tools and reveal that the two chatbots are perceived as increasing critical thinking skills in the current misinformation ecosystem.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1177/20563051221150407

Cites

54 of 54 references verified0 citation errors · 0 not checkable

Statistics

Figures

Image 1
CC-BY · From the PDF
Figure 1 System architecture.
Figure 1 System architecture.CC-BY · From the PDF
Figure 2 Example of reason-checking interaction through the Fake-News Immunity platform.
Figure 2 Example of reason-checking interaction through the Fake-News Immunity platform.CC-BY · From the PDF
Figure 3 Example of reason -checking interaction through the Vaccinating News Chatbot.
Figure 3 Example of reason -checking interaction through the Vaccinating News Chatbot.CC-BY · From the PDF
Figure 4 Personality traits of avatars preferred by the users.
Figure 4 Personality traits of avatars preferred by the users.CC-BY · From the PDF
Figure 5 Fallacies discovered by users while playing.
Figure 5 Fallacies discovered by users while playing.CC-BY · From the PDF
Figure 6 Users' responses to the critical thinking for media literacy scale.
Figure 6 Users' responses to the critical thinking for media literacy scale.CC-BY · From the PDF
Figure 7 Clustered Boxplot of total scores pre- and postinterventions.
Figure 7 Clustered Boxplot of total scores pre- and postinterventions.CC-BY · From the PDF
Figure 8 Example of fallacious news from social media (Instagram).
Figure 8 Example of fallacious news from social media (Instagram).CC-BY · From the PDF
Figure 9 Example of fallacious news from social media (Twitter).
Figure 9 Example of fallacious news from social media (Twitter).CC-BY · From the PDF

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 55 references

Research works printed but not linked: 4

  1. Facione P. A. (1990). The California critical thinking skills test: College level. Technical report #1—Experimental validation and content validity. https://www.researchgate.net/profile/Peter-Facione/publication/268295703_The_California_Critical_Thinking_Skills_Test_College_Level_Experimental_Validation_and_Content_Validity/links/587677f908aebf17d3b9a162/The-California-Critical-Thinking-Skills-Test-Co
  2. Hatcher D. L., 2005, Reasoning and writing: From critical thinking to composition
  3. Johnson R. H., 2006, Logical self-defense
  4. Mercier H., 2017, The enigma of reason: A new theory of human undersanding

Cited by

See all 38

Metadata

Authors
Musi, E., Carmi, E., Reed, C., Yates, S., & O’Halloran, K.
Affiliations
  • University of Liverpool (GB)
  • City, University of London (GB)
  • University of Dundee (GB)
Corresponding author
Musi, Elena
Venue
Social Media + Society
Published
2023-01
Volume
9
Issue
1
ISSN
2056-3051 (ISSN-L)
OpenAlex
W4318313270
Cited by
34
References
55
Citations by year
2026: 8 · 2025: 15 · 2024: 8 · 2023: 3
FWCI
14.67
Type
journal article
Language
en
Open access
Locations
  • Social Media + Society (publishedVersion, cc-by)
  • Discovery Research Portal (University of Dundee) (publishedVersion, cc-by)
  • City Research Online (City University London) (submittedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Social Sciences › Sociology and Political Science › Misinformation and Its Impacts
  • Physical Sciences › Computer Science › Information Systems › Spam and Phishing Detection
  • Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
Keywords
misinformation, fake news, inoculation theory, prebunking, fallacy theory, chatbots, multi-agent systems, critical thinking, persuasion, discourse theory, user interface design

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Developing Misinformation Immunity: How to Reason-Check Fallacious News in a Human–Computer Interaction Environment. https://app.cochat.ai/papers/10.1177/20563051221150407
The paper
Musi, E., Carmi, E., Reed, C., Yates, S., & O’Halloran, K. (2023). Developing Misinformation Immunity: How to Reason-Check Fallacious News in a Human–Computer Interaction Environment. Social Media + Society. https://doi.org/10.1177/20563051221150407

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.