Abstract:
Chatbots will likely play a more significant part in streamlining consumer interactions and
creating pleasant relationships between e-commerce platforms and their customers as
technology advances. This study investigates the influence of Artificial Intelligence (AI)-
based chatbots on customer support on e-commerce websites, a topic that has received
little attention in the literature. Recognizing the lack of research on the effects of AI-based
chatbots on customer service, this investigation tries to completely examine their impact
on the customer service experience in the e-commerce area. A rigorously developed questionnaire was presented to a sample size of 201 respondents to collect primary data
for this investigation. The questionnaire was designed to elucidate the unique impact of
AI-based chatbot capabilities on customer service on e-commerce platforms. As prediction
models, an array of classification technologies, including Naive Bayes, SVM, MLP, J48
and random forest, were used. The demographic distribution of the sample group revealed
a client base in Sri Lanka, with 48% male and 52% female respondents. Most participants
were between 25 and 33, with 52 being the least represented. Notably, the J48 decision
tree algorithm predicted the impact of AI-based chatbots on customer service with greater
accuracy. The precision value of 0.985, recall value of 0.985, F-measure value of 0.985,
MAE value of 0.3321, and RMSE value of 0.3345 highlight the J48 decision tree algorithm's resilience. These findings have significance for the refinement and augmentation of customer services on e-commerce platforms via the strategic integration
of AI-based chatbots.
