# Natural Language Processing in Customer Service: A Systematic Review

arXiv: https://arxiv.org/abs/2212.09523 · HTML: https://mlsanity.com/paper/2212.09523/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 33 references that are in the map.
- First posted on arXiv 16 Dec 2022.

## Builds on (most cited first, 3 of 3)

- [Touch Your Heart: A Tone-aware Chatbot for Customer Care on Social Media](https://mlsanity.com/paper/1803.02952/) (2018)
- ["How May I Help You?": Modeling Twitter Customer Service Conversations Using Fine-Grained Dialogue Acts](https://mlsanity.com/paper/1709.05413/) (2017)
- [HHH: An Online Medical Chatbot System based on Knowledge Graph and Hierarchical Bi-Directional Attention](https://mlsanity.com/paper/2002.03140/) (2020)

## Built on by (most cited first, 4 of 4)

- [Arabic Text Diacritization In The Age Of Transfer Learning: Token Classification Is All You Need](https://mlsanity.com/paper/2401.04848/) (2024)
- [Grading Conversational Responses Of Chatbots](https://mlsanity.com/paper/2303.12038/) (2023)
- [Towards Proactive Information Probing: Customer Service Chatbots Harvesting Value from Conversation](https://mlsanity.com/paper/2604.11077/) (2026)
- [MindFlow+: A Self-Evolving Agent for E-Commerce Customer Service](https://mlsanity.com/paper/2507.18884/) (2025)

## Abstract (arXiv)

Artificial intelligence and natural language processing (NLP) are increasingly being used in customer service to interact with users and answer their questions. The goal of this systematic review is to examine existing research on the use of NLP technology in customer service, including the research domain, applications, datasets used, and evaluation methods. The review also looks at the future direction of the field and any significant limitations. The review covers the time period from 2015 to 2022 and includes papers from five major scientific databases. Chatbots and question-answering systems were found to be used in 10 main fields, with the most common use in general, social networking, and e-commerce areas. Twitter was the second most commonly used dataset, with most research also using their own original datasets. Accuracy, precision, recall, and F1 were the most common evaluation methods. Future work aims to improve the performance and understanding of user behavior and emotions, and address limitations such as the volume, diversity, and quality of datasets. This review includes research on different spoken languages and models and techniques.