Agent Productivity Modeling in a Call Center Domain Using Attentive Convolutional Neural Networks

Measuring the productivity of an agent in a call center domain is a challenging task. Subjective measures are commonly used for evaluation in the current systems. In this paper, we propose an objective framework for modeling agent productivity for real estate call centers based on speech signal proc...

Full description

Saved in:
Bibliographic Details
Published inSensors (Basel, Switzerland) Vol. 20; no. 19; p. 5489
Main Authors Ahmed, Abdelrahman, Toral, Sergio, Shaalan, Khaled, Hifny, Yaser
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 25.09.2020
MDPI
Subjects
Accuracy
attention layer
Call centers
Classification
CNNs
Domains
Letter
LSTMs
Modelling
Neural networks
Performance evaluation
Productivity
Productivity measurement
productivity modeling
Real estate
Signal processing
Software
Speech
Support vector machines
Text categorization
Voice recognition
Online AccessGet full text

Cover

More Information
Summary:Measuring the productivity of an agent in a call center domain is a challenging task. Subjective measures are commonly used for evaluation in the current systems. In this paper, we propose an objective framework for modeling agent productivity for real estate call centers based on speech signal processing. The problem is formulated as a binary classification task using deep learning methods. We explore several designs for the classifier based on convolutional neural networks (CNNs), long-short-term memory networks (LSTMs), and an attention layer. The corpus consists of seven hours collected and annotated from three different call centers. The result shows that the speech-based approach can lead to significant improvements (1.57% absolute improvements) over a robust text baseline system.
Bibliography:SourceType-Other Sources-1
content type line 63
ObjectType-Correspondence-1
ISSN:1424-8220
1424-8220
DOI:10.3390/s20195489