Citation

Naveen, Palanichamy and Haw, Su Cheng and Nadthan, Devakumaran and Ramamoorthy, Saravana Kumar Improving Chatbot Performance using Hybrid Deep Learning Approach. Journal of System and Management Sciences, 13 (3). pp. 505-516. ISSN 1816-6075, 1818-0523

Text 16.pdf - Published Version Restricted to Repository staff only Download (547kB)

Abstract

A chatbot is a computer program that is implemented to communicate with clients via natural language. Suruhanjaya Syarikat Malaysia (SSM) is a Malaysian statutory authority that governs businesses and companies and it would benefit from implementing a chatbot for a multitude of reasons, including the pandemic which hinders the citizens from leaving their homes. However, there are several issues with current chatbots as they are unable to respond accurately to long queries. Furthermore, it has a significant response time which would discourage users from using chatbots. The aim of this study is to build a chatbot that efficiently handles extensive queries from users by providing contextually relevant responses. Long Short-Term Memory (LSTM) models are well-suited to handle long-term dependencies while Gated Recurrent Units (GRU) models are more efficient hence a hybrid model of GRU-LSTM is proposed as a solution. The performance evaluation metrics used are Bilingual Evaluation Understudy, BLEU and response time. The LSTM model obtains the highest BLEU score while the GRU model has the shortest response time. The proposed model has the second-best BLEU score outperforming the GRU model and the second-best response time outperforming the LSTM model. Hence, the proposed model is a good compromise between the two models as it has a reasonable BLEU score accuracy and response time.

Item Type:	Article
Uncontrolled Keywords:	C,hatbot, deep Learning
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics Q Science > QA Mathematics > QA71-90 Instruments and machines > QA75.5-76.95 Electronic computers. Computer science
Divisions:	Faculty of Computing and Informatics (FCI)
Depositing User:	Ms Nurul Iqtiani Ahmad
Date Deposited:	01 Aug 2023 02:19
Last Modified:	01 Aug 2023 02:19
URII:	http://shdl.mmu.edu.my/id/eprint/11596

Downloads

Edit (login required)