Komparasi Pengaruh Model Klasifikasi Naive Bayes dan Support Vector Machine Pada Analisis Data Sentimen Di Bidang Pendidikan

Some of the problems that often occur in the application of text mining processing are related to data pre-processing, feature selection, classification models, class imbalance, language dynamics, evaluation, and validation.The application of supervised machine learning techniques to classification models such as Naive Bayes and Support Vector Machines in sentiment analysis requires special attention to ensure accurate and reliable results.The purpose of this study is to evaluate how the Naive Bayes and Support Vector Machine classification models affect sentiment analysis, based on the results of several studies using these classification models in the field of education.The method in this study is a literature review with a search for research literature, inclusion and exclusion criteria, screening and selection process of research results, and assessment of research results that have been done before.The results of the literature review in this study show that the Naive Bayes and Support Vector Machine classification models can provide good accuracy values in sentiment analysis research, but combining the two models with an ensemble approach further improves accuracy.As for sentiment analysis research, there are several important factors that need to be considered, such as research contributions, data mining implementation methods, influencing parameters, data selection and extraction processes, data evaluation mechanisms, and the risk of failure.All of these factors are expected to be considered as a conceptual framework that will support success in sentiment analysis research for future research in the field of education.