This study introduces an improved BERT-based model for sentiment analysis in several languages, specifically focusing on analyzing e-commerce evaluations written in English and Bengali. Conventional sentiment analysis techniques frequently face difficulties in dealing with the subtle linguistic differences and cultural diversities present in datasets containing multiple languages. The model we propose integrates sophisticated methodologies and utilizes Local Interpretable Model-agnostic Explanations (LIME) to enhance the accuracy, interpretability, and dependability of sentiment assessments in various language situations. To tackle the challenges of sentiment categorization in a multilingual setting, we enhance the pre-trained BERT architecture by incorporating extra neural network layers. Compared to traditional machine learning and current deep learning methods, the model underwent a thorough evaluation, showcasing its superior capabilities with accuracy, precision, recall, and F1-score of 0.92. Including LIME improves the model’s transparency, allowing for a better understanding of the decision-making process and increasing user confidence. This research highlights the potential of utilizing advanced deep learning models to address the difficulties of sentiment analysis in global e-commerce environments, providing major implications for both academic research and practical applications in industry.

Along with the growth of the Internet, social media usage has drastically expanded. As people share their opinions and ideas more frequently on the Internet and through various social media platforms, there has been a notable rise in the number of consumer phrases that contain sentiment data. According to reports, cyberbullying frequently leads to severe emotional and physical suffering, especially in women and young children. In certain instances, it has even been reported that sufferers attempt suicide. The bully may occasionally attempt to destroy any proof they believe to be on their side. Even if the victim gets the evidence, it will still be a long time before they get justice at that point. This work used OCR, NLP, and machine learning to detect cyberbullying in photos in order to design and execute a practical method to recognize cyberbullying from images. Eight classifier techniques are used to compare the accuracy of these algorithms against the BoW Model and the TF-IDF, two key features. These classifiers are used to understand and recognize bullying behaviors. Based on testing the suggested method on the cyberbullying dataset, it was shown that linear SVC after OCR and logistic regression perform better and achieve the best accuracy of 96 percent. This study aid in providing a good outline that shapes the methods for detecting online bullying from a screenshot with design and implementation details.