Title: An intelligent chatbot using deep learning with bidirectional GRU and CNN model

Authors: Vaibhav Ghildiyal

Addresses: Sinch, One Alliance Center, 3500 Lenox Road NE Suite #1875, Atlanta, GA 30326, USA

Abstract: Chatbots can be an important tool for guiding users through various processes or providing information on a particular topic. One of the main benefits of chatbots is their ability to provide personalised and real-time assistance to users, without requiring them to navigate through complex interfaces or search for information on their own. In this paper, an intelligent chatbot is designed for guiding the person who came for interview in an organisation, it is maintained at the human resource (HR) department in the company. The questions asked by the candidate is first pre-processed using stop word removal, stemming, tokenisation. Then the features present in the pre-processed data are extracted using the POS bagging and bag of words (BOW) representation. The chimp optimisation algorithm is introduced for selecting the required features. Finally, the chatbot uses the hybrid convolutional neural network (CNN) with bi-directional gradient recurrent unit (Bi-GRU). The implementation of this deep learning based chatbot is performed using the PYTHON platform with accuracy of 93.12%.

Keywords: chatbots; human resource; stop word removal; stemming; tokenisation; bi-directional gradient recurrent unit; Bi-GRU.

DOI: 10.1504/IJMOR.2024.142137

International Journal of Mathematics in Operational Research, 2024 Vol.29 No.2, pp.258 - 270

Received: 13 May 2023
Accepted: 17 May 2023
Published online: 08 Oct 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article