Login or signup to connect with paper authors and to register for specific Author Connect sessions (if available).

Analyzing Anomalous Engagement and Commenter Behavior on YouTube
Shadi Shajari, Ridwan Amure, Nitin Agarwal

YouTube, a leading online content platform with billions of users worldwide, faces a troubling rise in anomalous behavior. This paper proposes a scoring that integrates engagement and commenter behavior metrics to assess channel anomalous behavior. Via analysis of engagement metrics such as comments, views, and subscriber counts, coupled with an examination of frequent commenter groups, the study employs methods like Harmonic Mean (HM), Weighted Average with Interaction Term (WAIT), and Agreement-Weighted Maximum (AWM). Our analysis uncovers widespread anomalous activities, encompassing 71 channels, 642,952 videos, 12,425,587 commenters, 123,882,200 comments, 83,396,188,807 views, and 139,985,870 subscribers. Focusing on channels associated with the US Air Force, news, and the Indo-Pacific region, the study provides insights into anomalous behavior on YouTube. Addressing integrity, this research aims to promote high-quality information dissemination, particularly in sensitive geopolitical contexts, to enhance the platform's credibility.

AuthorConnect Sessions

No sessions scheduled yet