Skripsi
ANALISIS SENTIMEN ULASAN TRIPADVISOR MENGGUNAKAN MODEL MULTILINGUAL XLM-ROBERTA
Sentiment analysis is one of the applications of Natural Language Processing (NLP) used to identify users’ opinions or evaluations toward a particular service or object. This study aims to develop a sentiment analysis system for Tripadvisor reviews using the Transformer-based XLM-RoBERTa model. The dataset used consists of 28.754 Italian-language Tripadvisor reviews classified into two sentiment categories, namely positive and negative. The research stages include data preprocessing, dataset splitting with an 80:10:10 ratio for training, validation, and testing data, model training using several hyperparameter scenarios, and performance evaluation using a confusion matrix with Accuracy, Precision, Recall, and F1-Score metrics. Based on the results of six experimental scenarios, the best model was obtained in Scenario 1 with a learning rate of 1e-5, batch size of 32, and 3 epochs. The model achieved an Accuracy of 0.9739, Precision of 0.9726, Recall of 0.9673, and F1-Score of 0.9699.
No other version available