Assessment of beliefs and attitudes towards benzodiazepines using machine learning based on social media posts: An observational Study. (Preprint)

Author:

De Anta Laura,Álvarez-Mon Miguel ÁngelORCID,Pereira Sánchez VictorORCID,Donat Vargas CarolinaORCID,Lara Abelanda Francisco,Arrieta Maria,Montero-Torres Maria,García Montero Cielo,Fraile-Martínez Oscar,Mora Fernando,Ortega Miguel Ángel,Álvarez Mon Melchor,Quintero Javier

Abstract

BACKGROUND

Benzodiazepines are frequently prescribed drugs. However, its prolonged use generates tolerance, dependence, and other adverse effects. Despite this, its long-term use is common, which is a public health problem.

OBJECTIVE

The objective of this study is to delve into the beliefs and opinions that the population has about benzodiazepines, since it can shed light on their pattern of use.

METHODS

We collected public tweets published in English between January 1, 2019 and October 31, 2020 that contained mentions to benzodiazepines. The content of each tweet and the characteristics of the users were analyzed using a mixed methodology that included manual analysis and semi-supervised machine learning.

RESULTS

More than half of Twitter users mentioned the good efficacy of benzodiazepines, speaking minimally about their side effects. The most active users in these conversations are the patients themselves and their families, being the presence of health professionals and institutions almost non-existent. On the other hand, the most named drugs coincide with those most prescribed by professionals.

CONCLUSIONS

Social media platforms provide information about the experiences and opinions that users have about a drug, and interestingly, their sentiment about benzodiazepines is positive, considering them effective drugs, without referring to side effects. This analysis indicates that there is a need to educate physicians, patients, and relatives of the potential risks associated with the use of benzodiazepines, as well as to promote clinical guidelines that help to manage these medications properly.

Publisher

JMIR Publications Inc.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3