New Research Shows Plugged Wells and Decreased Injection Rates Diminish Induced Earthquake Occurrences in Oklahoma

Wastewater injection resulting from oil and gas production in Oklahoma caused a dramatic rise in seismic activity in the state between 2009 and 2015. But regulatory efforts to backfill some injection wells with cement and reduce injection volumes have been effective in lowering the state's induced earthquake rate, according to a new study. Wastewater injection
HomeHealthSocial Media Insights: A New Frontier for Early Detection of PTSD Symptoms

Social Media Insights: A New Frontier for Early Detection of PTSD Symptoms

Scientists have studied a vast number of tweets to find out which COVID-19 survivors are experiencing post-traumatic stress disorder (PTSD). This research showcases how social media can be a valuable resource for early diagnosis and intervention.
Researchers have studied a vast number of tweets to find out which COVID-19 survivors are experiencing post-traumatic stress disorder (PTSD). This research showcases how social media can be a valuable resource for early diagnosis and intervention.

In their study, researchers compiled a dataset of 3.96 million Twitter posts from users who had reported being COVID positive between March 2020 and November 2021.

Using machine learning techniques such as Support Vector Machine (SVM), Naïve Bayes, K-Nearest Neighbors, and Random Forest, they categorized the tweets into PTSD positive or negative, achieving an accuracy rate of 83.29% with the SVM method.

Their results were published in Scientific Reports, where the international research team emphasized the significant mental health effects of COVID-19 and stressed the importance of early detection and intervention for PTSD.

Co-author Professor Mark Lee from the University of Birmingham remarked: “Our findings illustrate that social media can be an effective tool for identifying individuals at risk of PTSD, facilitating early screening and timely medical response.

“With further investigation, the machine learning methods explored in this study could be adapted for the early detection of other health concerns.”

While examining the tweets, the researchers pinpointed COVID-19 infection as a significant triggering event. They then sought symptoms related to key factors such as re-experiencing, hyperarousal, and avoidance, searching for various keywords, including:

  • Flashbacks, nightmares, intrusions, panic, vivid dreams (re-experiencing)
  • Agitated, startled, hypervigilant, irritable (hyperarousal)
  • Avoid, avoidance (avoidance behavior)
  • Anxiety, depressed, suicidal thoughts, appetite, trauma, fatigue (other symptoms)

Tweets that indicated both a COVID-19 diagnosis and included PTSD-related keywords were classified as ‘PTSD Positive.’ In contrast, those that mentioned PTSD keywords but were related to other situations were categorized as ‘PTSD Negative.’

Co-author Dr. Mubashir Ali from the University of Birmingham noted: “We have gained better insight into users’ posting habits following their COVID-19 diagnosis. Our analysis shows that the pandemic has greatly affected mental health, highlighting issues like anxiety, insomnia, and nightmares that are prevalent among COVID-19 survivors.”

PTSD is an anxiety disorder that can arise in people who have faced traumatic experiences, such as a car accident, armed conflict, abuse (physical, emotional, or sexual), a natural disaster, or other significant life changes. Both the WHO and the American Psychiatric Association (APA) recognize PTSD as a genuine condition.