22 Oct2020

A machine learning approach to infant distress calling and maternal behaviour of wild chimpanzees

A machine learning approach to infant distress calling and maternal behaviour of wild chimpanzees

Guillaume Dezecache, Klaus Zuberbühler, Marina Davila-Ross & Christoph D. Dahl

In this research, we tackled the long-standing, widely-debated and cross-disciplinary question of whether highly graded infant distress cries carry information about the nature of the external event triggering them that could guide parenting decisions. Distress calls are an acoustically variable group of vocalizations ubiquitous in mammals and other animals. Their presumed function is to recruit help, but there has been much debate on whether the nature of the disturbance can be inferred from the acoustics of distress calls alone. Here, we used machine learning to analyse episodes of distress calling of wild infant chimpanzees. We extracted exemplars from distress calling episodes and classified , and examined them in relation to the external event triggering them and the distance to the mother. In further steps, we tested whether the acoustic variants were associated with particular maternal behaviours. Our results suggest that, although infant chimpanzee distress calls are highly graded, they can convey information about discrete events (notably types of problems experienced by the infant and distance to the mother), which in turn may guide maternal parenting decisions. The extent to which mothers rely on acoustical (versus visual) information to decide upon intervening should be the focus of future research.

Published in Animal Cognition

Here is the link: in press