[Paper Review] Coronavirus on Social Media: Analyzing Misinformation in Twitter Conversations.

Karishma Sharma, Sungyong Seo+4 more|arXiv (Cornell University)|Mar 26, 2020

Misinformation and Its Impacts8 references52 citations

TL;DR

This study analyzes misinformation about COVID-19 on Twitter from March 1 to June 5, 2020, using streaming data and fact-checking sources to identify misleading content. It reveals narratives, engagement patterns, and trends in misinformation, publishing real-time insights via a public dashboard to enhance transparency and inform public discourse.

ABSTRACT

The ongoing Coronavirus (COVID-19) pandemic highlights the inter-connectedness of our present-day globalized world. With social distancing policies in place, virtual communication has become an important source of (mis)information. As increasing number of people rely on social media platforms for news, identifying misinformation and uncovering the nature of online discourse around COVID-19 has emerged as a critical task. To this end, we collected streaming data related to COVID-19 using the Twitter API, starting March 1, 2020. We identified unreliable and misleading contents based on fact-checking sources, and examined the narratives promoted in misinformation tweets, along with the distribution of engagements with these tweets. In addition, we provide examples of the spreading patterns of prominent misinformation tweets. The analysis is presented and updated on a publically accessible dashboard (this https URL) to track the nature of online discourse and misinformation about COVID-19 on Twitter from March 1 - June 5, 2020. The dashboard provides a daily list of identified misinformation tweets, along with topics, sentiments, and emerging trends in the COVID-19 Twitter discourse. The dashboard is provided to improve visibility into the nature and quality of information shared online, and provide real-time access to insights and information extracted from the dataset.

Motivation & Objective

• To understand the nature and spread of misinformation about COVID-19 on social media during the early pandemic phase.
• To identify unreliable and misleading content on Twitter using external fact-checking sources as ground truth.
• To analyze the narratives, sentiments, and engagement patterns associated with misinformation tweets.
• To provide real-time, publicly accessible insights into the quality and dynamics of online discourse about COVID-19.
• To support public health communication by improving visibility into misinformation trends on Twitter.

Proposed method

• Collected real-time Twitter streaming data related to COVID-19 using the Twitter API from March 1 to June 5, 2020.
• Identified misinformation by cross-referencing tweets with fact-checking sources to label unreliable content.
• Categorized misinformation tweets by dominant narratives, sentiments, and topics using natural language processing and manual labeling.
• Tracked engagement metrics (e.g., retweets, likes) to analyze the virality and reach of misinformation.
• Visualized and updated findings daily in a public dashboard to ensure real-time access to insights.
• Provided a continuously updated dataset and analysis to monitor evolving trends in online discourse about the pandemic.

Experimental results

Research questions

• RQ1 What types of narratives and false claims were most prevalent in misinformation shared on Twitter during the early phase of the COVID-19 pandemic?
• RQ2 How did engagement metrics (likes, retweets) correlate with the spread of misinformation on Twitter?
• RQ3 What were the dominant sentiments and topics associated with misleading COVID-19 content on the platform?
• RQ4 How did the volume and nature of misinformation evolve over time from March 1 to June 5, 2020?
• RQ5 What role did social media play in amplifying or containing false information about the pandemic during this period?

Key findings

• The study identified a significant volume of misinformation on Twitter related to COVID-19, with false claims often centered on transmission, treatments, and origins.
• Misinformation tweets were frequently shared with high engagement, indicating strong virality despite fact-checking efforts.
• Common narratives included conspiracy theories about the virus’s origin, false cures, and exaggerated claims about case numbers and mortality rates.
• Sentiment analysis revealed that misinformation often carried negative or sensationalist tones, amplifying fear and distrust.
• The public dashboard provided real-time visibility into emerging misinformation trends, enabling timely monitoring and response.
• The analysis demonstrated that social media platforms like Twitter played a central role in shaping public perception through the rapid spread of unverified claims.