Computer Science > Computers and Society
[Submitted on 3 Sep 2026]
Title:Affective publics in Arabic YouTube
View PDF HTML (experimental)Abstract:What is the emotional register of Arabic YouTube's affective publics? To investigate this, we analyzed 67,725 YouTube comments collected around socio-political topics associated with Yemen, Saudi Arabia, Iraq, Jordan, and Syria using a unified sentiment-and-emotion pipeline. Our results profile a single regional affective public rather than five separate national ones. Sentiment is overwhelmingly negative across all five country-oriented corpora, and the country-level emotion profiles are structurally similar. This shared register still accommodates some regional variations: discourse is organized around country-level political actors and cross-border historical trauma figures, and grief singularizes Iraq from the other countries. The differences in emotional register also tracks lived political causes rather than fixed categories, which we observe from patterns of the valence of US-related content, that tracks the presence or absence of direct US military engagement. Our work shows that the emotional register of Arabic YouTube's affective publics is a shared one that is historically layered and geographically conditioned, which has implications for public diplomacy in the MENA region.
Submission history
From: Lynnette Hui Xian Ng [view email][v1] Thu, 3 Sep 2026 01:50:44 UTC (2,140 KB)
References & Citations
Loading...
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Facts Only
* Lynnette Hui Xian Ng submitted the work on September 3, 2026.
* The study analyzed 67,725 YouTube comments.
* The data focuses on socio-political topics related to Yemen, Saudi Arabia, Iraq, Jordan, and Syria.
* A unified sentiment-and-emotion pipeline was used for analysis.
* Sentiment across all five country-oriented corpora is overwhelmingly negative.
* Country-level emotion profiles are structurally similar.
* Discourse involves country-level political actors and cross-border historical trauma figures.
* Grief is identified as a distinguishing emotion for Iraq.
* The valence of US-related content correlates with the presence or absence of direct US military engagement.
* The findings concern the emotional register of affective publics in the MENA region.
Executive Summary
Arabic YouTube discourse surrounding socio-political issues in Yemen, Saudi Arabia, Iraq, Jordan, and Syria reveals a unified regional affective public rather than distinct national ones. Analysis of over 67,000 comments shows that sentiment is consistently negative across these geographies, with structurally similar emotional profiles. This suggests a shared emotional register across the MENA region that is shaped by historical layers and geographic conditions.
While the overarching emotional tone is shared, specific variations exist based on lived political experiences. For example, grief is more prominent in Iraqi discourse, and reactions to the United States vary depending on whether there has been direct military engagement in a specific country. This indicates that while the emotional framework is regional, it is conditioned by specific political actors and historical traumas. These dynamics have direct implications for how public diplomacy is conducted within the region.
Full Take
This scholarship employs a quantitative approach to mapping "affective publics," using a sentiment-and-emotion pipeline to process a substantial dataset. A peer reviewer would likely query the specific parameters of the "unified pipeline"—specifically how it handles Arabic dialects (diglossia) and sarcasm, which are prevalent in YouTube comments and can skew sentiment analysis. The sample size is robust, but the reliance on YouTube comments introduces a selection bias toward users who are more emotionally charged or politically active.
The central claim—that a single regional affective public exists—is well-supported by the structural similarity of the emotion profiles. The authors avoid overclaiming by acknowledging "geographic conditioning," particularly regarding US military intervention. This suggests that emotional registers are not static cultural traits but are responsive to material political realities. This extends existing knowledge by shifting the focus from national identity to shared regional trauma and political experience.
For these findings to matter outside of computational social science, practitioners of public diplomacy must recognize that national-level messaging may be ineffective if the underlying emotional driver is a cross-border regional sentiment.
Bridge Questions:
1. How would the results change if the dataset included platforms with different algorithmic curation, such as X (Twitter) or TikTok?
2. To what extent does the "overwhelmingly negative" sentiment reflect actual public opinion versus the incentive structures of YouTube's engagement algorithms?
3. Would the "single regional public" hold if the study included North African Arabic-speaking countries?
Sentinel — Human
This text exhibits the high coherence and specialized vocabulary expected from academic research, strongly suggesting it is human-authored content detailing specific analytical findings.
