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. 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.

results

The binary logistics regression model reported higher predictive accuracies of empathy (AUC=0.617, 95% CI: 0.613-0.622) compared to the GAMM (AUC=0.605, 95% CI:0.601-0.609) and the random forest model (AUC= 0.600, 95% CI: 0.595-0.604). This difference was statistically significant, as evidenced by the non-overlapping 95% confidence intervals obtained for AUC. The Delong test further validated these results, showing a significant difference in the binary logistic model compared to Random Forest (D=6.443, df =186283, P<.001) and GAMM (Z = 5.846, P<.001). These findings confirm that the binary logistic regression model outperforms the other two models in terms of predictive accuracy for empathy classification.

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.

clinicaltrial