Optimizing Customer Trust And Satisfaction In E-Commerce With Machine Learning Techniques

Abstract

Establishing trust is vital for sustainable success in a constantly changing e-commerce marketplace, particularly in locations such as Bangladesh where trust among customers is usually lacking. This research study focuses on assessing the sentiment of customer reviews in Bangladesh's e-commerce industry. It employs several Machine Learning approaches, with a primary emphasis on Natural Language Processing (NLP). The major purpose is to evaluate patterns and sentiments in Bengali review in order to give organizations with insights into customer preferences and enhance the quality of their offerings, ultimately establishing trust. This study investigates the usefulness of Natural Language Processing in managing a substantial number of Bengali e-commerce reviews, while taking into consideration particular linguistic and contextual distinctive characteristics. The study attempts to acquire key insights from consumer opinions in order to better products and services, enhance customer happiness, and achieve an advantage over others in the e-commerce industry of our country. Also, the anticipated outputs of the sentiment analysis could serve to boost the accomplishment and progress of Bangladesh's ecommerce business by overcoming potential barriers associated to data-driven initiatives that depend mostly on feedback from users. The study methodology is made up acquiring data from Kaggle and successfully preparing the text employing natural language processing techniques. To increase the statistical results of the models, the Decision Tree Classifier, K-nearest Neighbor approach, Random Forest Classifier, Logistic Regression, and Naive Bayes Classifier methods use unigram, bigram, and trigram data. The study produced an accuracy rate of 80.59% by applying the Logistic Regression algorithm by incorporating the trigram feature.