This study aims to analyze the sentiment of iPhone product reviews from Amazon using the BERT (Bidirectional Encoder Representations from Transformers) model to classify reviews as either positive or negative. The dataset, sourced from Kaggle, includes text reviews and star ratings, where high ratings indicate positive sentiment and low ratings indicate negative sentiment. After text preprocessing steps, including data cleaning, tokenization, and sentiment labeling, the BERT model was fine-tuned for sentiment classification, with the data split into training, validation, and test sets. Evaluation results demonstrate that the BERT model achieves a high classification accuracy, with an accuracy rate of 93.9% and a balanced F1 score between precision and recall. Confusion matrix evaluation also indicates that the model consistently identifies both positive and negative sentiments. This study shows that Transformer-based models like BERT are highly effective in understanding customer opinions in e-commerce, with broad application potential for data-driven decision-making in marketing strategies and product development.

Android is an operating system whose capabilities continue to increase from year to year. The capabilities of Android currently match the capabilities of a computer. Not only limited to ordinary computers, what a server computer can do can now be done on Android, including making Android a web server. So it is possible for people who have Android to have their own web server. The problem that arises is that the web server on Android cannot be accessed directly via the internet. Cellular operators do not provide Public IP to their customers, so a way is needed so that the Android web server can be accessed on the internet, one of which is by using Virtual Private Network (VPN) technology. The aim of this research is to make the web server on Android accessible on the internet. The method used is to combine a Virtual Private Server (VPS) and Android using VPN. The research results showed that VPN can be a bridge so that the web server on Android can be accessed from the internet.  

Effective sales transaction management is very important for retail businesses. This research aims to develop a comprehensive sales invoice information system at the Sari Agung Semarang store to improve the efficiency and accuracy of the sales process. The system is designed to simplify invoicing, maintain accurate inventory records, and provide complete sales reporting capabilities. This research involved analysis of current sales processes, system design with a user-friendly interface, and integration with existing accounting and inventory management software. Implementation of this system is expected to increase customer satisfaction, reduce the risk of errors, and provide valuable insights to support better decision making.