Say, for example, if you have a health problem.
In a new study, researchers were able to predict 21 types of health problems – ranging from pregnancy to skin disorders – by analyzing Facebook profiles of people.
The updates on Facebook were "particularly effective in predicting diabetes and mental health issues, including anxiety, depression, and psychosis," the study revealed.
The study will be published on June 19 in PLOS One, a peer-reviewed open access scientific journal published since 2006.
"People's personality, mental state and health behaviors are all reflected in their social media and all have a huge impact on health," the study said.
To conduct this study, researchers linked the electronic medical records of consenting patients to their social media.
In total, they reviewed 949,530 Facebook status updates on 999 participants whose messages had more than 500 words.
The researchers identified a language that probably indicates the behavior or symptoms characteristic of certain diagnoses. For example, publications that mentioned "drink", "drunk" or "bottle" were marked for alcohol abuse.
However, the study warned that predictive words are not necessarily causal mechanisms. Nevertheless, social media models have a predictive value and could open up new possibilities for personalizing health care.
Questions about personal data
"The power of social media language to predict diagnoses raises parallel questions about privacy, informed consent, and ownership of data," the researchers wrote.