Healthcall Corpus and Transformer Embeddings from Healthcare Customer-Agent Conversations
Nikola Lackovic, Claude Montacié, Cédric Lequilliec, Marie-José Caraty
Abstract
We present the corpus called HealthCall which was recorded in real-life conditions in the call center of Malakoff Humanis a health insurance company. The records include two separate audio channels, the first one for the customer and the second one for the agent. This corpus includes a transcription of the spoken conversations and was divided into three sets: training (Train), development (Dev) and test (Test) sets. Two customer relationship management tasks were assessed on the HealthCall corpus: the classification of user requests and the detection of complaints. For this purpose, we have investigated 18 feature sets: 12 linguistic and 6 audio sets. We have used BERT models for the linguistic features and Wav2Vec models for the audio features. The results show that the linguistic features give always the best results (92.7% for the Request task and 69.0% for the Complaint task) but the concatenation of acoustic and linguistic features allows a slight improvement for the Complaint task (69.4% versus 69%).
BibTeX
@inproceedings{icassp2023_healthcallcorpus,
title = {Healthcall Corpus and Transformer Embeddings from Healthcare Customer-Agent Conversations},
author = {Nikola Lackovic and Claude Montacié and Cédric Lequilliec and Marie-José Caraty},
booktitle = {ICASSP 2023},
year = {2023}
}