Scholars@Duke publication: Detecting customer complaint escalation with recurrent neural networks and manually-engineered features

Detecting customer complaint escalation with recurrent neural networks and manually-engineered features

Publication , Conference

Yang, W; Tan, L; Lu, C; Cui, A; Li, H; Chen, X; Xiong, K; Wang, M; Li, M; Pei, J; Lin, J

Published in: NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference

January 1, 2019

Consumers dissatisfied with the normal dispute resolution process provided by an ecommerce company's customer service agents have the option of escalating their complaints by filing grievances with a government authority. This paper tackles the challenge of monitoring ongoing text chat dialogues to identify cases where the customer expresses such an intent, providing triage and prioritization for a separate pool of specialized agents specially trained to handle more complex situations. We describe a hybrid model that tackles this challenge by integrating recurrent neural networks with manually-engineered features. Experiments show that both components are complementary and contribute to overall recall, outperforming competitive baselines. A trial online deployment of our model demonstrates its business value in improving customer service.

Duke Scholars

Author Jian Pei Computer Science

Published In

NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference

Publication Date

January 1, 2019

Volume

Start / End Page

56 / 63

Citation

APA

Chicago

ICMJE

MLA

NLM

Yang, W., Tan, L., Lu, C., Cui, A., Li, H., Chen, X., … Lin, J. (2019). Detecting customer complaint escalation with recurrent neural networks and manually-engineered features. In NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference (Vol. 2, pp. 56–63).

Yang, W., L. Tan, C. Lu, A. Cui, H. Li, X. Chen, K. Xiong, et al. “Detecting customer complaint escalation with recurrent neural networks and manually-engineered features.” In NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, 2:56–63, 2019.

Yang W, Tan L, Lu C, Cui A, Li H, Chen X, et al. Detecting customer complaint escalation with recurrent neural networks and manually-engineered features. In: NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference. 2019. p. 56–63.

Yang, W., et al. “Detecting customer complaint escalation with recurrent neural networks and manually-engineered features.” NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, vol. 2, 2019, pp. 56–63.

Yang W, Tan L, Lu C, Cui A, Li H, Chen X, Xiong K, Wang M, Li M, Pei J, Lin J. Detecting customer complaint escalation with recurrent neural networks and manually-engineered features. NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference. 2019. p. 56–63.

Published In

NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference