twitter dataset

Data were collected through the Twitter API, focusing on specific vocabulary related to wildfires, hashtags commonly used during the Tubbs Fire, and terms and hashtags related to mental health, well-being, and physical symptoms associated with smoke and wildfire exposure. We focused exclusively on the period from October 8 to October 31, aligning precisely with the duration of the Tubbs Fire. The final dataset available for analysis consists of 90,759 tweets.


 We provide two datasets extracted from Twitter, in Spanish and English, and annotate each one with approximately 1,500 users who have been diagnosed with one of nine different mental disorders (ADHD, Autism, Anxiety, Bipolar, Depression, Eating disoders, OCD, PTSD and Schizophrenia) along with 1,700 matched-control users.