# Affective Dimensions in Maternal Voice During Child Feeding in Mothers With and Without Eating Disorder History—Findings From a Machine Learning Analysis of Speech Data

## TL;DR

The study uses machine learning to find that mothers with eating disorder history show stronger emotional expression in their voices during child feeding compared to those without.

## Contribution

This is the first study to use machine learning to analyze vocal affective dimensions in maternal communication during feeding in mothers with and without eating disorder history.

## Key findings

- Mothers with eating disorder history showed stronger emotional arousal, valence, and dominance in their voices during child feeding.
- Emotional hotspots occurred predominantly in the middle of feeding interactions for mothers with eating disorder history.
- Machine learning models detected more subtle emotional nuances compared to traditional questionnaires.

## Abstract

Eating disorder (ED) history may impact mother‐child communication during mealtimes and contribute to transgenerational transmission of ED. This study employed machine learning (ML) to identify speech characteristics during mother‐child feeding interactions, aiming for investigating whether vocalised affective characteristics differ between mothers with and without ED history when feeding their child.

Mothers with (n = 17) and without ED history (n = 27) and their children (10 months) were filmed at home during mealtime. Various ML models were exploratively tested to assess their suitability for analysing maternal voice data. Diagnosis of an ED history was based on the structured Eating Disorder Examination Interview.

A ML model specialised for the prediction of emotional arousal, valence and dominance provided the most pronounced differences between the groups. These variables were consistently stronger expressed in the voices of mothers with ED history during child feeding, predominantly in the middle of the interaction.

Voice data suggests that mothers with ED history might be emotionally stronger involved throughout child feeding. This indicates that there are differences in communication between women with and without ED history and highlights the importance of research into maternal communication in affected families. ML approaches are promising tools as they can detect more subtle nuances compared to questionnaires.

Differences in affective dimensions of the voices of mothers with and without ED history were found, highlighting the need for further research to explore the role of communication in the transmission of ED.Mothers with ED history expressed stronger emotionality in their voices throughout child feeding, with ‘emotional hotspots’ generally occurring in the middle of the feeding interaction.ML approaches are promising tools as they can detect more subtle nuances compared to questionnaires.

Differences in affective dimensions of the voices of mothers with and without ED history were found, highlighting the need for further research to explore the role of communication in the transmission of ED.

Mothers with ED history expressed stronger emotionality in their voices throughout child feeding, with ‘emotional hotspots’ generally occurring in the middle of the feeding interaction.

ML approaches are promising tools as they can detect more subtle nuances compared to questionnaires.