In the context of the escalating global spam activity, supported by data from CNN Indonesia in 2021, this research aimed to investigate the root causes and characteristics of this phenomenon. The approach employed in this study involved a series of exploration and classification stages of text messages with the clear objective: to determine whether each message fell into the spam category or not, utilizing the Naïve Bayes method. Additionally, the research aimed to identify the factors influencing the status of text messages, whether they were considered as spam or not. The Naïve Bayes classification method was chosen to facilitate the process of identifying spam-related messages. The dataset used in this research had an 80:20 ratio and was obtained from the Department of Communication and Informatics of Asahan Regency. This data was used to train and test the developed classification model. Data labeling processes were conducted to uncover the factors influencing the status of text messages as spam or non-spam. The research findings indicated that issues related to spam and non-spam messages remained a serious concern. The high accuracy rate, reaching 92%, achieved by the Naïve Bayes method in classifying messages, demonstrated the effectiveness of the method in detecting spam messages.
Copyrights © 2024