Literatur Review: Application of Naive Bayes Data Mining Process for Social Media Analysis

Abstract

In data processing, the naïve bayes method is used as the main algorithm in the data mining process. The selection of this method is based on the advantages of naïve bayes in processing text data efficiently. With this approach, public opinion recorded in uploads on social media can be grouped into positive, negative, or neutral sentiment categories. The research process begins with data collection from social media, then text pre-processing is carried out such as data cleaning. The naïve Bayes model is then trained to recognize opinions based on the available dataset. The results of this study indicate that social media can be a source of data for public opinion analysis. In addition, the naïve Bayes method has proven effective in grouping public opinion. This analysis can be an input for policy makers, business actors, and academics to find out the public's voice objectively. This study contributes to the development of social media-based data mining studies in Indonesia. Thus, this approach is expected to support more responsive decision making towards public opinion in the digital space.