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...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/19/5489 |
| _version_ | 1827705487364194304 |
|---|---|
| author | Abdelrahman Ahmed Sergio Toral Khaled Shaalan Yaser Hifny |
| author_facet | Abdelrahman Ahmed Sergio Toral Khaled Shaalan Yaser Hifny |
| author_sort | Abdelrahman Ahmed |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T16:03:42Z |
| format | Article |
| id | doaj.art-7715c68aecd0497bb57875fa1b1dae8e |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T16:03:42Z |
| publishDate | 2020-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-7715c68aecd0497bb57875fa1b1dae8e2023-11-20T15:03:00ZengMDPI AGSensors1424-82202020-09-012019548910.3390/s20195489Agent Productivity Modeling in a Call Center Domain Using Attentive Convolutional Neural NetworksAbdelrahman Ahmed0Sergio Toral1Khaled Shaalan2Yaser Hifny3Department of Electronics Engineering, University of Seville, 41092 Seville, SpainDepartment of Electronics Engineering, University of Seville, 41092 Seville, SpainFaculty of Informatics, The British University in Dubai, Dubai 345015, UAEFaculty of Computer Sciences and Information, Helwan University, Helwan 11795, EgyptMeasuring 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.https://www.mdpi.com/1424-8220/20/19/5489productivity modelingLSTMsCNNsattention layer |
| spellingShingle | Abdelrahman Ahmed Sergio Toral Khaled Shaalan Yaser Hifny Agent Productivity Modeling in a Call Center Domain Using Attentive Convolutional Neural Networks Sensors productivity modeling LSTMs CNNs attention layer |
| title | Agent Productivity Modeling in a Call Center Domain Using Attentive Convolutional Neural Networks |
| title_full | Agent Productivity Modeling in a Call Center Domain Using Attentive Convolutional Neural Networks |
| title_fullStr | Agent Productivity Modeling in a Call Center Domain Using Attentive Convolutional Neural Networks |
| title_full_unstemmed | Agent Productivity Modeling in a Call Center Domain Using Attentive Convolutional Neural Networks |
| title_short | Agent Productivity Modeling in a Call Center Domain Using Attentive Convolutional Neural Networks |
| title_sort | agent productivity modeling in a call center domain using attentive convolutional neural networks |
| topic | productivity modeling LSTMs CNNs attention layer |
| url | https://www.mdpi.com/1424-8220/20/19/5489 |
| work_keys_str_mv | AT abdelrahmanahmed agentproductivitymodelinginacallcenterdomainusingattentiveconvolutionalneuralnetworks AT sergiotoral agentproductivitymodelinginacallcenterdomainusingattentiveconvolutionalneuralnetworks AT khaledshaalan agentproductivitymodelinginacallcenterdomainusingattentiveconvolutionalneuralnetworks AT yaserhifny agentproductivitymodelinginacallcenterdomainusingattentiveconvolutionalneuralnetworks |