The researchers wanted to analyze massive data shared on social networks to provide new opportunities to better understand the behavior of their users.
Behavioral and linguistic changes in tweets in Spanish published by Twitter users suffering from depression and who are taking medication to treat this disease were identified by researchers of the Research Programme on Biomedical Informatics (GRIB) from UPF and Hospital del Mar Medical Research Institute (IMIM), according to a press release.
Depression affects more than 322 million people of all ages and is among the leading causes of disability worldwide, according to the World Health Organization. The researchers wanted to analyze massive data shared on social networks to provide new opportunities to better understand the behavior of their users.
In the study, the research team used Big Data and text mining to examine tweets by users who mentioned they were taking drugs for the treatment of depressive disorders. The objective was to detect the effects of this medication through changes in the language used in their tweets or in the way these people used Twitter.
Previous studies observed Twitter users who potentially suffer from depression display specific behavioral and linguistic features, according to the researchers.
The results showed that during periods in which users stated they were receiving antidepressant drug treatment, their Twitter activity increased with longer messages but posting fewer messages at night. Further, these users interacted more with other users and experienced an increase in positive emotions related to happiness and surprise.
“We can state that the behavioral patterns of people who are in treatment with antidepressant drugs change and tend to resemble those of people who do not suffer from depression,” said study author Angela Leis in a press release.
There are limitations to this study, such as its specific focus on a serotonin reuptake inhibitor, which is the most commonly prescribed drug for treating depression, according to the authors.
“We analyzed changes in behavioral and linguistic features in the tweets posted while users were in treatment, in comparison with tweets posted by the same users when it was less likely that they were taking these drugs,” said study author Francesco Ronzano in a press release.
Included in the final study were 186 users and their timelines with 668,842 tweets.
“The use of techniques based on Big Data and text mining, which enable detecting changes in the way in which users interact in their social networks, such as Twitter, can provide us with new opportunities to follow up and monitor patients suffering from one of the most widespread, disabling health problems as is depression,” said research lead Ferran Sanz, full professor with the UPF Department of Experimental and Health Sciences (DCEXS) and director of GRIB of the IMIM and UPF, in a press release.
The effects of treatment with antidepressant drugs evaluated through the analysis of patients’ tweets. Universitat Pompeu Fabra Barcelona. https://www.upf.edu/web/focus/ciencies-de-la-salut-i-de-la-vida/-/asset_publisher/M1rzWRjhDOMp/content/id/243188507/maximized#.YC1LtJNKhTY. Published February 11, 2021. Accessed February 17, 2021.