Sentiment Mining in E-Commerce: The Transformer-based Deep Learning Model

Abstract

Sentiment analysis is crucial for comprehending customer feedback and enhancing workplace culture, as well as improving products and services. By employing natural language processing (NLP) techniques to meticulously analyze this feedback, organizations can identify specific areas that require improvement, address employee issues, and cultivate a positive work environment. These deep learning models powered by NLP offer invaluable tools for HR and sales departments in the e-commerce sector, enabling them to track sentiment trends among employees and users over time and implement targeted interventions. Focusing on the e-commerce industry, this study employs NLP-driven deep learning methodologies to analyze both employee and user feedback, with the objective of identifying underlying sentiments. The proposed framework leverages these advanced techniques to categorize user feedback into positive, negative, or neutral sentiments. This approach aims to develop a robust and effective system for sentiment analysis, providing significant insights that can help drive organizational improvements and enhance customer satisfaction. The key steps of this framework include data collection, NLP-enhanced feature extraction, sentiment detection, and final classification using finite-state automata. The effectiveness of this NLP-centric approach was tested on diverse datasets of customer feedback collected from an e-commerce industry. Evaluation metrics such as accuracy, precision, and recall were utilized to assess the performance of the system. The results demonstrate the effectiveness of the proposed framework, achieving a 93.75% accuracy rate and surpassing existing benchmark methods. The outcomes of this study are particularly consequential for the e-commerce sector, offering them a strategic advantage in refining their product portfolios and cultivating a more dynamic workplace culture