In an era where online content can sway public opinion and shape narratives, the influence of YouTube comment sections cannot be underestimated. Anomalous commenter behavior, which often includes organized groups of commenters who collaborate to manipulate public opinion, can disseminate false information and influence discussions, particularly on topics related to sensitive geopolitical and potential economic growth regions such as the Indo-Pacific. Thus, the need for detection mechanisms to assess and quantify anomalous commenter behavior on YouTube channels becomes critical, not only for safeguarding the platform but also for ensuring the quality of information and discussions in this significant area. This study centers on YouTube channels related to the Indo-Pacific region and introduces unsupervised learning methods for detecting anomalous commenter behavior on these channels. Our dataset includes 35 YouTube channels, 308,890 videos, 726,078 commenters, and 1,536,284 comments. The research objective is to assign a normalized score, ranging from 0 to 1, that shows the level of anomalous commenter behavior on each channel. This is accomplished by employing a combination of methods such as Kernel Density Estimation (KDE), Gaussian Mixture Model (GMM), comment activity analysis, and qualitative analysis.