Globally, there has been a significant increase in the number of people using prescription drugs for reasons other than why they were prescribed, sometimes combining them with other substances such as alcohol to sleep better or stimulants to perform better. A team of computer scientists and emergency physicians from Emory, Oregon, and Pennsylvania universities in the United States used AI to analyze drug misuse and the emotions users felt during times of use. The study, “Large-Scale Social Media Analysis Reveals Emotions Associated with Nonmedical Prescription Drug Use,” was published in the journal Health Data Science.
In 2021, more than 108,000 people in the U.S. died from drug overdoses, a number that is up 20% from 2020, many of these deaths were caused by the ingestion of prescription drugs, often mixed with other substances. In France, more than 10,000 people die each year as a result of medication misuse.
The use of non-medical prescription drugs (NMPDU) mainly concerns opioids, central nervous system stimulants and benzodiazepines. Studies of its influence on mental health are based on surveys that have shown that SUDs involving opioids are strongly associated with psychiatric disorders. For example, an analysis of data from the National Survey on Drug Use and Health (NSDUH) found associations between opioid abuse and risk factors for suicide.
However, while studies have attempted to characterize the reasons for NMPDU, they do not address the emotional state of users. With recent research showing that social media can fill in some of the gaps in these traditional survey-based studies, the team analyzed approximately 137 million messages from 87,718 Twitter users in terms of emotions, feelings, concerns, and possible reasons for NMPDU via natural language processing.
Large-scale analysis of twitter messages reveals emotions associated with nonmedical prescription drug use
In this study, researchers used natural language processing (NLP) and machine learning approaches to investigate a large Twitter dataset of three common prescription drug categories and their combinations (opioids, benzodiazepines, stimulants, and polysubstances (abuse of two or more different categories of NMPDUs at the same time, commonly referred to as coingestion) to investigate and answer the following key research questions:
- How does the emotional content expressed in the Twitter profiles of the NMPDU groups differ from that expressed in the Twitter profiles of the non-NMPDU groups (control group)?
- How do NMPDU tweets differ sentimentally from non-NMPDU tweets?
- How do the personal, social, biological, and fundamental concerns expressed in the Twitter profiles of NMPDU groups differ from those expressed in the Twitter profiles of non-NMPDU groups?
They also used thematic modeling on NMPDU tweets to extract potential reasons for non-medical use of each drug category, and compared the distributions (of all the above variables) between men and women.
These large-scale data analyses show that there are substantial differences between the message texts of self-reporting SUD users on Twitter and the control group, and between male and female reporters.
Male users expressed higher anger and lower positivity, happiness, anticipation, and sadness. In terms of social and personal content, compared to male users, female users shared more content related to social life (friends and family), health, and personal concerns (at home). However, there were consistent differences between the different categories of medications.
Although social media-based monitoring systems are not a replacement for traditional systems, they can offer complementary information. Thus, the knowledge gained from this study could help tailor outreach and intervention programs to targeted cohorts to mitigate the impact of prescription drug misuse.
“Large-Scale Social Media Analysis Reveals Emotions Associated with Nonmedical Prescription Drug Use” Health Data Science, https://doi.org/10.34133/2022/9851989
Mohammed Ali Al-Garadi,1 Yuan-Chi Yang,1YutingGuo,2SangmiKim,3JenniferS. Love,4 Jeanmarie Perrone,5AbeedSarker.1,6
1Departmentof Biomedical Informatics, School of Medicine, Emory University, Atlanta, GA, USA
2Departmentof Computer Science, Emory University, Atlanta, GA, USA
3Schoolof Nursing, Emory University, Atlanta, GA, USA
4Departmentof Emergency Medicine, School of Medicine, Oregon Health & Science University, Portland, OR, USA
5Departmentof Emergency Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA
6Departmentof Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, USA