Heena Sharma Blog

Language people use in their Facebook posts can predict a future diagnosis of depression as accurately as the tools clinicians use in medical settings to screen for the disease, suggests new research. "Social media data contain markers akin to the genome," said one of the researchers Johannes Eichstaedt from University of Pennsylvania in the US. "With surprisingly similar methods to those used in genomics, we can comb social media data to find these markers. Depression appears to be something quite detectable in this way," Eichstaedt said. For the study, published in the journal Proceedings of the National Academy of Sciences (PNAS), the researchers identified data from nearly 1,200 people consenting to share Facebook statuses and electronic medical-record information. They then analysed the statuses using Machine Learning techniques to distinguish those with a formal depression diagnosis. Analysing social media data shared by the particip...

As per a new study, pregnant women who have suffered from depression or bipolar disorder recognise baby faces and how babies laugh or cry differently. This happens even if they are not currently experiencing depressive or manic symptoms, although the authors stresses that research would be needed to confirm any long-term effects. Researchers compared 22 pregnant women, currently well but with a history of depression, and seven with bipolar disorder who were also currently well, against 28 healthy pregnant women. They also tested 18 non-pregnant women, as controls. Between the 27th and 39th weeks of pregnancy , all the women were tested for how they responded to a series of happy or sad faces, and to laughter and crying, of both babies and adults. Specifically, the women were asked to rate how happy or distressed the infants were based on infants' facial and vocal displays of emotion. They were also asked to identify adult facial expressions of emotion across varyi...