Follow us
pubmed meta image 2
🧑🏼‍💻 Research - January 2, 2025

Piecing together the narrative of #longcovid: an unsupervised deep learning of 1,354,889 X (formerly Twitter) posts from 2020 to 2023.

🌟 Stay Updated!
Join Dr. Ailexa’s channels to receive the latest insights in health and AI.

⚡ Quick Summary

This study analyzed 1,354,889 tweets related to long COVID from May 2020 to April 2023, utilizing unsupervised deep learning techniques to uncover public narratives. The findings reveal three main themes: general discussions, skepticism, and adverse effects, highlighting the ongoing public discourse surrounding long COVID.

🔍 Key Details

  • 📊 Dataset: 2,905,906 initial tweets, 1,354,889 unique English-language tweets
  • 🧩 Features used: Tweets containing #long-covid, #long_covid, or “long covid”
  • ⚙️ Technology: Bidirectional Encoder Representations from Transformers (BERT)
  • 🏆 Analysis methods: Topic modeling and reflexive thematic analysis

🔑 Key Takeaways

  • 📊 Three main themes emerged from the analysis: general discussions, skepticism, and adverse effects of long COVID.
  • 💡 Public awareness and community support were significant aspects of the discourse.
  • 👥 Misinformation was identified as a critical challenge in the long COVID conversation.
  • 📈 Stable temporal trends indicate sustained public interest in long COVID discussions from 2020 to 2023.
  • 🌍 Social media played a vital role in shaping public perception and awareness of long COVID.
  • 🤝 Collective effort in community building and information sharing was evident in the posts analyzed.

📚 Background

The emergence of long COVID has sparked significant public interest and concern since the onset of the COVID-19 pandemic. As individuals continue to experience lingering symptoms long after the initial infection, understanding the public narrative surrounding this condition is crucial. Social media platforms, particularly X (formerly Twitter), serve as a rich source of real-time public sentiment and discourse, making them ideal for analyzing community perspectives and experiences.

🗒️ Study

This study, conducted by a team of researchers, aimed to characterize the public conversations around long COVID by analyzing tweets from May 2020 to April 2023. By employing unsupervised deep learning techniques, specifically BERT, the researchers processed a vast dataset of tweets to identify and categorize themes that reflect the evolving narrative of long COVID in public discourse.

📈 Results

The analysis revealed three primary themes: (1) general discussions about long COVID, (2) skepticism regarding its existence and impact, and (3) the adverse effects experienced by individuals. These themes underscore the complexity of public sentiment, highlighting both support and skepticism within the community. The study also noted a stable temporal trend in discussions, indicating that interest in long COVID has remained consistent over the years.

🌍 Impact and Implications

The findings of this study have significant implications for public health communication and community support initiatives. By understanding the narratives surrounding long COVID, health professionals and policymakers can better address misinformation and foster a supportive environment for those affected. The role of social media in shaping public awareness cannot be understated, as it serves as a platform for sharing experiences and building community resilience.

🔮 Conclusion

This study highlights the importance of analyzing social media discourse to understand public perceptions of long COVID. The insights gained from the analysis of over a million tweets reveal a complex interplay of support, skepticism, and personal experiences. As we continue to navigate the challenges posed by long COVID, leveraging social media narratives can enhance our understanding and response to this ongoing public health issue.

💬 Your comments

What are your thoughts on the public discourse surrounding long COVID? How do you think social media influences our understanding of health issues? 💬 Share your insights in the comments below or connect with us on social media:

Piecing together the narrative of #longcovid: an unsupervised deep learning of 1,354,889 X (formerly Twitter) posts from 2020 to 2023.

Abstract

OBJECTIVE: To characterize the public conversations around long COVID, as expressed through X (formerly Twitter) posts from May 2020 to April 2023.
METHODS: Using X as the data source, we extracted tweets containing #long-covid, #long_covid, or “long covid,” posted from May 2020 to April 2023. We then conducted an unsupervised deep learning analysis using Bidirectional Encoder Representations from Transformers (BERT). This method allowed us to process and analyze large-scale textual data, focusing on individual user tweets. We then employed BERT-based topic modeling, followed by reflexive thematic analysis to categorize and further refine tweets into coherent themes to interpret the overarching narratives within the long COVID discourse. In contrast to prior studies, the constructs framing our analyses were data driven as well as informed by the tenets of social constructivism.
RESULTS: Out of an initial dataset of 2,905,906 tweets, a total of 1,354,889 unique, English-language tweets from individual users were included in the final dataset for analysis. Three main themes were generated: (1) General discussions of long COVID, (2) Skepticism about long COVID, and (3) Adverse effects of long COVID on individuals. These themes highlighted various aspects, including public awareness, community support, misinformation, and personal experiences with long COVID. The analysis also revealed a stable temporal trend in the long COVID discussions from 2020 to 2023, indicating its sustained interest in public discourse.
CONCLUSION: Social media, specifically X, helped in shaping public awareness and perception of long COVID, and the posts demonstrate a collective effort in community building and information sharing.

Author: [‘Ng QX’, ‘Wee LE’, ‘Lim YL’, ‘Ong RHS’, ‘Ong C’, ‘Venkatachalam I’, ‘Liew TM’]

Journal: Front Public Health

Citation: Ng QX, et al. Piecing together the narrative of #longcovid: an unsupervised deep learning of 1,354,889 X (formerly Twitter) posts from 2020 to 2023. Piecing together the narrative of #longcovid: an unsupervised deep learning of 1,354,889 X (formerly Twitter) posts from 2020 to 2023. 2024; 12:1491087. doi: 10.3389/fpubh.2024.1491087

Share on facebook
Facebook
Share on twitter
Twitter
Share on linkedin
LinkedIn
Share on whatsapp
WhatsApp

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.