Postnatal depression, also known as postpartum depression, is a type of depression which can affect women after giving birth. Microsoft has discovered a way to predict postnatal depression by monitoring a woman's Twitter feed, weeks before the birth of the child.
It all has to do with the language she uses on Twitter. The algorithm has nothing to do with the woman tweeting about her pregnancy or her unborn baby, rather it deals with the subtle verbal cues that unveil her unhappiness or anxiety. For example, a rise in the number of words like 'hate', 'disappointed', and the increased use of the word 'l' are all cues that the woman will face postnatal depression.
"We saw several patterns in the language of women with post-natal depression. Then we wondered if we could go back in time and see if this trend could be spotted before the birth. And we found we could. We found that two to three weeks before the birth the same clues were there in around 80 per cent of cases. It's very subtle. It's things like an increase in the word 'frustrated' and, for example, they curse more often," Eric Horvitz, co-director at Microsoft Research, stated.
Postnatal depression typically occurs during the first three months after delivery and causes all sorts of issues in women, including sadness, the feeling of being overwhelmed, guilt, low self-esteem, social withdrawal, the feeling of not being good enough to take care of the child, and much more. Horvitz adds that a higher usage of a first-person pronoun can indicate an onset of depression, because the woman has become more self-focused.
Microsoft is basing these findings off a study that analyzed the language of nearly 3,000 woman, three months prior to the birth of their child and three months after the birth of the child. Microsoft has discovered that 15% of women who were diagnosed with postnatal depression had asked more questions, had lower levels of positivity, and increased levels of anger and anxiety.
There should be an app for that, as Horvitz believes an app can be designed that offers women facts on how to identify the depression before it happens and how to deal with it. "It's not one for Microsoft, but a welfare group could create an app that women could run on a smartphone which warns them of the onset of depression and points them to resources to help them deal with it," Horvitz added.