{"id":1246,"date":"2017-09-29T11:30:18","date_gmt":"2017-09-29T10:30:18","guid":{"rendered":"http:\/\/blogs.kent.ac.uk\/unikentcomp-news\/?p=1246"},"modified":"2017-09-29T11:30:39","modified_gmt":"2017-09-29T10:30:39","slug":"ai-can-predict-whether-your-relationship-will-last-based-on-how-you-speak-to-your-partner","status":"publish","type":"post","link":"https:\/\/blogs.kent.ac.uk\/unikentcomp-news\/2017\/09\/29\/ai-can-predict-whether-your-relationship-will-last-based-on-how-you-speak-to-your-partner\/","title":{"rendered":"AI can predict whether your relationship will last based on how you speak to your partner"},"content":{"rendered":"

Ian McLoughlin<\/a>, University of Kent<\/a><\/em><\/p>\n

Any child (or spouse) who has been scolded for their tone of voice \u2013 such as shouting or being sarcastic \u2013 knows that the way<\/em> you speak to someone can be just as important as the words<\/em> that you use. Voice artists and actors make great use of this \u2013 they are skilled at imparting meaning in the way that they speak, sometimes much more than the words alone would merit.<\/p>\n

But just how much information is carried in our tone of voice and conversation patterns and how does that impact our relationships with others? Computational systems can already establish who people are from their voices<\/a>, so could they also tell us anything about our love life? Amazingly, it seems like it.<\/p>\n

New research, just published in the journal PLOS-ONE<\/a>, has analysed the vocal characteristics of 134 couples undergoing therapy. Researchers from the University of Southern California used computers to extract standard speech analysis features from recordings of therapy session participants over two years. The features \u2013 including pitch<\/a>, variation in pitch and intonation \u2013 all relate to voice aspects like tone and intensity.<\/p>\n

A machine-learning algorithm was then trained to learn a relationship between those vocal features and the eventual outcome of therapy. This wasn\u2019t as simple as detecting shouting or raised voices \u2013 it included the interplay of conversation, who spoke when and for how long as well as the sound of the voices. It turned out that ignoring what was being said and considering only these patterns of speaking was sufficient to predict whether or not couples would stay together. This was purely data driven, so it didn\u2019t relate outcomes to specific voice attributes.<\/p>\n