Interactive Chatbot for improving the Text Classification Data Quality

Document Type

Article

Publication Date

Spring 3-1-2024

Abstract

he pandemic is affecting the global community in many ways. In mostdeveloping countries, there is a limitation in the detection facilities, which affectmany suspected cases. This paper proposes a chatbot framework to assist andprovide guide for the suspected/infected patients with COVID-19. Conversationalsoftware agents activated by natural language processing is known as chatbot, arean excellent example of such machine. Our COVID Bot is based on an integratedmodel between the rule-based model and the class classification model, havingthe rule-based model integrated with the MongoDB NoSQL database. Chatbot,using Natural Language Processing (NLP) and data mining techniques to assistpatients by providing immediate answers for their questions. It also acts as a novelcommunication mean for impaired people for sharing knowledge and information,through conversing with them. Based on the literature review, this paper comparedour methods with three classical classification algorithms: random forest, gradientboosting, and multi-layer perceptron (MLP). Experimental results show that ourproposed chatbot greatly improves the classification performance, with IE-Net as94.80%, 92.79% as recall, 92.97% as precision and 94.93% as AUC for distin-guishing COVID-19 cases from non-COVID-19 cases (with only common clinicaldiagnose data) (PDF) Interactive Chatbot for Improving the Text Classification Data Quality.

Link to Full Text

Share

COinS