For example, tell if you have a disease.
In a new study, researchers were able to predict 21 types of diseases – from pregnancy to skin diseases – by analyzing people's Facebook profiles.
Facebook status updates were "particularly effective in predicting diabetes and mental illness, including anxiety, depression, and psychosis," the study found.
The study will be published on June 19 in PLOS One, a peer-reviewed open access scientist journal published since 2006
"People's personality, mental state, and health behaviors are reflected in their social media and have a huge impact on health, "the study said.
To conduct the study, researchers have joined consenting patients with each other. "Electronic patient records using their social media."
In total, they reviewed 949,530 Facebook status updates for 999 participants whose posts were over 500 words.
Researchers identified a language that is likely to indicate the characteristic behavior or symptoms of certain diagnoses For example, posts mentioning "drink", "drunk" or "bottle" were tagged for alcohol abuse.
However, the study warned that predictive words are not necessarily causal mechanisms. Patterns have predictive value and could lead to new ways of personalizing healthcare.
Questions about personal information
"The ability of the social media language to predict diagnoses raises parallel questions about privacy, Declaration of consent and data ownership ", the researchers wrote.