The Structure of Participation and Attention in Arabic-Language Hezbollah Discourse on X
Mohamed Soufan

TL;DR
This study analyzes Arabic-language Hezbollah discourse on X, revealing a highly unequal distribution of engagement where a small minority of accounts attract most attention, despite broad participation in posting.
Contribution
It provides a detailed analysis of participation and attention structure in Hezbollah discourse on X, highlighting disparities among account types and engagement levels.
Findings
Top 1% of users capture 61.5% of engagement
Media accounts receive higher engagement per tweet
Most content is produced by non-media users, but attention is concentrated among few accounts
Abstract
Social media platforms play an increasingly important role in shaping political discussion and information flows. This study examines the structure of participation and attention in Arabic-language discourse about Hezbollah on X (formerly Twitter). Using a dataset of 15,767 tweets posted by 8,148 users between March 1 and March 8, 2026, the analysis investigates how engagement is distributed across participants and whether certain types of accounts play a disproportionate role in attracting attention. The results reveal a highly unequal distribution of engagement. Although thousands of users participate in the conversation, the top 1% of users capture 61.5% of all engagement, while the top 10% capture 96.2%. At the same time, most content is produced by non-media users, who account for 89.6% of users and 79.9% of tweets in the dataset. Accounts labeled as media, identified through…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
