Analysis of User-Generated Posts on Social Media of Adjuvant Analgesics: A Machine Learning Study
2025

Analysis of Social Media Posts on Pain Medications

Sample size: 51167 publication Evidence: moderate

Author Information

Author(s): Carabot Federico, Donat-Vargas Carolina, Lara-Abelenda Francisco J., Martínez Oscar Fraile, Santoma Javier, Garcia-Montero Cielo, Valadés Teresa, Rojas Luis Gutierrez, Martinez-González MA, Ortega Miguel Angel, Alvarez-Mon Melchor, Alvarez-Mon Miguel Angel

Primary Institution: University of Alcala

Hypothesis

What are the public opinions and perceptions regarding co-analgesics as expressed on social media?

Conclusion

The study reveals that public perceptions of co-analgesics are largely negative, with many users discussing low efficacy and side effects.

Supporting Evidence

  • 78% of posts discussed anticonvulsants, while 24% discussed analgesic antidepressants.
  • 70% of medical content noted low medication efficacy.
  • Almost 50% of posts referenced side effects.
  • 67% of posts were authored by patients.

Takeaway

People on social media often talk about pain medications, and many think they don't work well and have side effects.

Methodology

The study analyzed 77,183 social media posts about co-analgesics, with 51,167 deemed classifiable, using machine learning and manual coding.

Potential Biases

The analysis may be influenced by the subjective nature of content classification and the potential for data leakage in the training/testing split.

Limitations

The study's findings may not be generalizable due to the skewed demographics of Twitter users and potential exclusion of relevant posts using different keywords.

Participant Demographics

The majority of posts were from patients, with a smaller representation from healthcare professionals and institutions.

Statistical Information

P-Value

p<0.001

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.7150/ijms.96981

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication