RETRACTED: Enhanced E-commerce decision-making through sentiment analysis using machine learning-based approaches and...

Area of Science:

• E-commerce technology
• Applied machine learning
• Internet of Things (IoT) integration

Background:

• E-commerce is crucial for global trade and consumer convenience.
• Integrating IoT and machine intelligence can significantly improve e-commerce operations and decision-making.
• Current e-commerce strategies can be enhanced by analyzing customer data for personalized experiences and operational efficiency.

Purpose of the Study:

• To elevate the online shopping experience through advanced data analysis.
• To leverage IoT devices and machine learning (ML) for improved e-commerce decision-making.
• To develop adaptive retail strategies through customer behavior analysis and demand forecasting.

Main Methods:

• Utilized Internet of Things (IoT) devices to collect customer behavior and preference data.
• Applied various machine learning (ML) algorithms including logistic regression, Naïve Bayes, Support Vector Machine (SVM), Random Forest (RF), AdaBoosting, Gated Recurrent Unit (GRU), and Long Short-Term Memory (LSTM).
• Evaluated model performance using metrics such as F1 score, accuracy, precision, and recall, comparing traditional ML with deep learning techniques.

Main Results:

• AdaBoosting demonstrated superior performance over deep learning models (LSTM, GRU) and other ML techniques.
• AdaBoosting achieved an accuracy of 88%, an F1-score of 0.927, precision-1 of 0.908, and recall-1 of 0.947.
• Most ML techniques showed similar performance with count vectorizer and TD-IDF vectorizer, except for SVM.

Conclusions:

• The integration of IoT and ML, particularly AdaBoosting, significantly enhances e-commerce capabilities.
• This approach leads to more efficient operations, better demand forecasting, and increased customer satisfaction.
• The study paves the way for a new era of customer-centric, adaptive, and efficient retail strategies in e-commerce.