Study shows correlation between the number of tweets on mental health issues and urgent crisis referrals
As a part of a UK research group, Assistant Professor Leon Derczynski, conducted a study that revealed a correlation between increases in the number of urgent mental health-related crisis referred to two mental healthcare providers in London on days and a high number of tweets mentioning depression and schizophrenia. The study has been published in one of the world's leading science journals, Nature's Scientific Reports.
Leon DerczynskiComputer Science Departmenthealthsocial media
Written 11 February, 2020 11:07 by Jari Kickbusch
Previous studies have suggested that top-stories in the media on mental health issues may be associated with negative mental health outcomes. However, there has been a lack of knowledge on the impact of discussions and stories around the same issues on social media. Now, assistant professor at the IT University of Copenhagen, Leon Derczynski, has contributed to the relatively new research field.
As a part of UK of the research group - headed by Dr. Anna Kolliakou from King's College London - Leon Derczynski has contributed to a study comparing the number of tweets containing keywords associated with two important health disorders ― depression and schizophrenia ― with recorded referrals for urgent crisis episodes to two mental healthcare providers in London. After comparing the data from a four year period (2010-2014) the researchers have found 5-15% increases in the number of urgent mental crisis episodes referred to mental healthcare providers.
- The research found a correlation between how people discuss mental health on social media, and how many mental health-related clinical incidents there were. This can not only help medics predict when to look out for sensitive people in the community, but also help us measure how many people are be in trouble that aren't noticed by - or don't contact - professionals who can help them.
In the study Leon Derczynski has been contributing with search, analysis and extraction of terabytes of data and billions of social messages. He hopes that the results of the study will lead to increased focus on how social media affects mental vulnerable people and how hospitals can improve their interaction with the communities they support. Looking at the first responses on the study, he has reason to be optimistic. On the 6th of February an article describing the study and its findings was published in Nature's Scientific Reports, one of the world's leading science journals.
- This kind of rigorous study driven by huge amounts of publicly available data can help health services over the world better protect and look after their communities. It enables technology that could, for example, highlight in real-time when the vulnerable are most at risk. While this study is for the English, developing tools like this for the Danes is an important next step for our country, with so many people active on social media. In the future, it could be possible to identify these trends before they happen, and offer help even early to young and vulnerable people, says Leon Derczynski.
Read the article in
Nature
Jari Kickbusch, phone 7218 5304, email jark@itu.dk