Building Customer Support Chatbots With Intent Recognition

Abstract

In recent years, chatbots have emerged as a promising tool for delivering healthcare services. Chatbots can provide 24/7 access to healthcare information, improve patient engagement, and reduce the workload of healthcare professionals. However, building effective chatbots for healthcare requires expertise in natural language processing (NLP), machine learning, and healthcare domain knowledge. Chatbots have become increasingly popular in recent years, thanks to advancements in natural language processing (NLP) and machine learning (ML) technologies. One critical component of chatbots is intent recognition, which enables them to understand the user's purpose and respond appropriately. In this paper, we present a comparative study of different machine learning algorithms for intent classification in chatbots. We evaluate the performance of four ML algorithms: logistic regression, random forest, support vector machines (SVM), and deep learning (DL) neural networks, using a publicly available dataset. Our results show that SVM model outperform the other two algorithms in terms of accuracy and F1 score.