The information we post online could reveal insights into our mental health. In fact, according to US experts, it may spot key symptoms of depression and low-mood - months before a doctor's formal diagnosis. Researchers believe an algorithm could potentially scan a person's social media posts and alert them to linguistic red flags which are symptomatic of the condition. Indicators of the condition included mentions of hostility and loneliness, words like'tears' and'feelings', plus use of more first-person pronouns like'I' and'me'. Insight: Indicators of the condition included mentions of hostility and loneliness, words like'tears' and'feelings', plus use of more first-person pronouns like'I' and'me' Researchers from the University of Pennsylvania and Stony Brook University published their work in the Proceedings of the National Academy of Sciences.