JMIR Publications

ABSTRACT

Background:

The research study aimed to detect the vocal features immersed in empathic counsellor speech using samples of calls to a mental health (MH) helpline service.

Objective:

The study aimed to produce an algorithm for the identification of empathy from these features, which could act as a training guide for counsellors and conversational agents who need to transmit empathy in their vocals.

Methods:

Two annotators with a psychology background and English heritage provided empathy ratings for 57 calls involving female counsellors, as well as multiple short call segments within each of these calls. These ratings were found to be well correlated between the two raters in a sample of six common calls. Using vocal feature extraction from call segments and statistical variable selection methods, such as L1 penalised Least Absolute Shrinkage and Selection Operator (LASSO) and forward selection, a total of 14 significant vocal features were associated with empathic speech.

Results:

Generalised additive mixed models (GAMM), binary logistics regression with splines and random forest models were employed to obtain an algorithm that differentiated between high and low empathy call segments. Slightly higher predictive accuracies of empathy were reported from the binary logistics regression model (AUC=0.617) than the GAMM (AUC=0.605) and the random forest model (AUC= 0.600).

Conclusions:

This study suggests that the identification of empathy from vocal features alone is challenging and further research involving multi-modal models (e.g. models incorporating facial expression, words used and vocal features) are encouraged for detecting empathy in the future. This study has several limitations including a relatively small sample of calls and only two empathy raters. Future research should focus on accommodating multiple raters with varied backgrounds, to explore these effects on perceptions of empathy. In addition, considering counsellor vocals from larger more heterogeneous populations, including mixed-gender samples, will allow an exploration of the factors influencing the level of empathy projected in counsellor voices more generally.