A Suitable Technique for Enhancing Arabic-Language Consumer Sentiment Analysis Using Natural Language Processing and Stacking Machine Learning Model

When deciding on a product, sentiments expressed on social media or online reviews are important information sources.Positive and negative feedback from customers posted on social media platforms could substantially impact a business's bottom line.As a result, the development of effective and efficient approaches for classifying emotion has emerged as one of the most pressing concerns for businesses.Applying machine learning is widely regarded as one of the most effective and beneficial ways.This work will investigate how well Machine Learning (ML) techniques can comprehend Arabic sentiments.The Term Frequency-Inverse Document Frequency algorithm (TF-IDF) was used to extract the dataset's characteristics.As a consequence of this, the algorithms known as Random Forest (RF), Decision Tree (DT), Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), support vector machine (SVM), Quadratic Discriminant Analysis (QDA), logistic regression (LR), Gradient Boosting Regression Trees (GBRT), and Stochastic Gradient Descent (SGD) Classifier are used in the process of sentiment analysis (SA).To sum everything up, a stacked machine-learning model was developed.Compared to existing machine learning simple classifiers, our stacked model with 10-fold cross-validation shows a higher accuracy, precision, Cohen's Kappa, recall, and F1-score in the three different Arabic datasets used, which are the Hotel Arabic-Reviews Dataset (A), the Books Reviews in Arabic Dataset (B), and the Arabic Reviews dataset (C).