Scientists from Eötvös Loránd University in Hungary are developing a computer program that differentiates the acoustic features of dog barks, and classifies them according to different contexts. Led by Csaba Molnar, researchers recorded 6,000 barks made by 14 Mudis, Hungarian sheepdogs, in “stranger,” “fight,” “walk,” “alone,” “ball” and “play” situations. The algorithm correctly classified the emotional state of the dogs 43% of the time. “Since we have no reasons to say that Mudis are special among other dog breeds, I am pretty sure that this method for categorizing barks could work in other dog breeds,” Molnár told London's Daily Telegraph.