TY - GEN
T1 - A fast-training approach using ELM for satisfaction analysis of call centers
AU - Liu, Jing
AU - Zhang, Yingnan
AU - Hu, Jin
AU - Xie, Xiang
AU - Huang, Shilei
PY - 2017/1/13
Y1 - 2017/1/13
N2 - Analysis of the customers' satisfaction guarantees the improvement of service quality in call centers. In this paper, an intelligent satisfaction recognition system is introduced to analyze the customers' satisfaction through the customers' emotion recognition. The nature dialogues are collected from the Chinese call center. Support Vector Machine (SVM) and Extreme Learning Machine (ELM) are used for the mapping model respectively. According to the experiment, the best F score of SVM is 0.71. Compared to SVM, the best F of ELM is up to 0.723. The training time of SVM ranges from 1268s to 5002s while ELM's only ranges from 7.28s to 15.82s, with a decrease of 99%. ELM shortens the training time largely without damaging the performance. Because of the faster training speed, ELM is more beneficial to the model updating in real time. Therefore, ELM has a great edge on online learning.
AB - Analysis of the customers' satisfaction guarantees the improvement of service quality in call centers. In this paper, an intelligent satisfaction recognition system is introduced to analyze the customers' satisfaction through the customers' emotion recognition. The nature dialogues are collected from the Chinese call center. Support Vector Machine (SVM) and Extreme Learning Machine (ELM) are used for the mapping model respectively. According to the experiment, the best F score of SVM is 0.71. Compared to SVM, the best F of ELM is up to 0.723. The training time of SVM ranges from 1268s to 5002s while ELM's only ranges from 7.28s to 15.82s, with a decrease of 99%. ELM shortens the training time largely without damaging the performance. Because of the faster training speed, ELM is more beneficial to the model updating in real time. Therefore, ELM has a great edge on online learning.
KW - Call centers
KW - ELM
KW - Emotion recognition
KW - SVM
KW - Satisfaction analysis
UR - http://www.scopus.com/inward/record.url?scp=85018663092&partnerID=8YFLogxK
U2 - 10.1145/3036290.3036313
DO - 10.1145/3036290.3036313
M3 - Conference contribution
AN - SCOPUS:85018663092
T3 - ACM International Conference Proceeding Series
SP - 143
EP - 147
BT - Proceedings of 2017 International Conference on Machine Learning and Soft Computing, ICMLSC 2017
PB - Association for Computing Machinery
T2 - 2017 International Conference on Machine Learning and Soft Computing, ICMLSC 2017
Y2 - 13 January 2017 through 16 January 2017
ER -