Title: Sentiment Method Analysis in the Context of Information System Security: Comparison of Naive Bayes, K-Nearest Neighbor, and Random Forest
Authors: Ardian Ariadi and Danny Manongga
Volume: 9
Issue: 2
Pages: 45-49
Publication Date: 2025/02/28
Abstract:
This research explores sentiment analysis methods within the context of information system security, focusing on the comparison of three popular machine learning algorithms: Naive Bayes, K-Nearest Neighbor (K-NN), and Random Forest. The objective is to assess the effectiveness and efficiency of each algorithm in identifying and categorizing sentiments expressed in security-related content, such as user reviews, forum discussions, and cybersecurity reports. Through a series of experiments, this research evaluates the accuracy, precision, and recall of these models in processing textual data, while also considering computational complexity and scalability. The findings reveal key insights into the strengths and weaknesses of each algorithm in the context of sentiment analysis for information system security, with implications for improving security measures and user feedback analysis. The results underscore the importance of selecting the right algorithm depending on the specific needs and constraints of a given security system.