DEVELOPMENT OF THE NATURAL LANGUAGE PROCESSING-BASED CHATBOT FOR SHOPPRITE SHOPPING MALL
Duru Juliet Chinenye, Austine Ekekwe Duroha, Nkwocha Mcdonald · International Journal of Engineering Applied Sciences and Technology · 2022
Software-as-a-service (SaaS) solutions are frequently used to create chatbots, giving users the option to interact with them via desktop computers, mobile phones, and tablets. To increase customer accessibility, a chatbot is being developed for customers. The user can choose their own convenient language because the device offers text or audio support. This project's goal was to develop a chatbot for the Shopprite Shopping Mall. The chatbot's goal is to converse with the client in a clever, accurate, and timely manner using natural language processing. Customers can use this feature to communicate with the bot and ask questions about specific things they want to buy and the price before visiting the mall.Customers can access the chatbot from portable mobile devices or laptops at any time, making it possible to offer a round-the-clock online service. The discomfort customers feel when they visit the Shopprite shopping mall to look for things only to discover that they are either unavailable or out of stock will be lessened by the results of this study. The following methodologies were used to carry out the work: React.js to create the chatbot's front-end and admin login page; Spacy and React.ai to train the chatbot's NLP section andE-commerce datasets for the chatbot and MySQL to manage and create the data structure that will house the e-commerce datasets.It is recommended that new capabilities be added to the chatbot, such as the delivery of purchased things to a customer's home, more training phrases to give the chatbot a better social outlook, automated item addition to the chatbot database, and even adding a barcode reader option. Testing the chatbot using a bigger dataset would also be helpful.