Skip to content

VictorSuarezL/healthmisinfo-tweets

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

healthmisinfo-tweets

Paper Title: Assessing the Role of Social Bots During the COVID-19 Pandemic: Infodemic, Disagreement, and Criticism

Overview

Social media has revolutionized communication, presenting both opportunities and challenges, especially during crises like the COVID-19 pandemic. This project delves into the role of social bots during the pandemic, exploring their impact on information dissemination, public discourse, and sentiment analysis on Twitter.

Abstract

The project aims to investigate the influence of social bots on COVID-19-related conversations on Twitter. Through data collection, bot classification, topic modeling, and sentiment analysis, it uncovers distinct patterns in bot-driven discourse compared to human-generated content. The findings reveal significant differences in conversation topics and sentiment, shedding light on the potential implications for public health communication and policy responses.

Methodology

  1. Data Collection: Utilizing the Twitter streaming API, tweets related to COVID-19 were gathered during the early stages of the pandemic.
  2. Bot Classification: Botometer, a tool for bot detection, was employed to assess the likelihood of each Twitter account being a bot.
  3. Topic Modeling: Employing topic-modeling techniques, the Twitter conversation was analyzed to identify prevalent themes and content categories.
  4. Sentiment Analysis: Sentiment analysis was conducted to evaluate the emotional tone associated with tweets based on their source (bot, non-bot).

Results

  • Conversation Topics: Significant variations were observed among different account types. Non-bot accounts primarily discussed pandemic evolution, support, and advice. Self-declared bots focused on news updates and scientific findings, while bots predominantly engaged in political discourse, characterized by criticism and disagreement.
  • Sentiment Analysis: Non-bot accounts exhibited positive sentiment, whereas bots tended towards negativity, with self-declared bots maintaining a neutral stance.

Conclusion

By discerning bot accounts and employing topic modeling, this study segmented COVID-19 discourse on Twitter. Bots emerged as prominent sources of criticism and skepticism towards pandemic measures and information credibility. Understanding these dynamics is crucial for combating misinformation and fostering constructive dialogue on social media platforms.

Keywords

Botometer, COVID-19, Twitter stream, chatbot, epidemics, health promotion, infodemics, infodemiology, misinformation, outbreaks, pandemic, peer support, social media, social media bot.

For further details, please refer to the full publication.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published