Original title: Affective publics in Arabic YouTube
Lynnette Hui Xian Ng, Craig Douglas Albert, Abdullah Melhem, Ahmed Aleroud +1 · September 2026
Online communities often form around shared feelings about political issues. Researchers wanted to know the emotional tone of Arabic YouTube discussions. They studied comments on videos about five Middle Eastern nations: Yemen, Saudi Arabia, Iraq, Jordan, and Syria. A computer system analyzed the sentiments and feelings expressed in the text. They discovered that instead of five separate national groups, commenters act as one large regional community. Most of the reactions were negative across all five countries, and they shared similar emotional patterns. Discussions centered on local political leaders and shared historical trauma. Iraq stood out because its comments showed unique levels of grief. Finally, feelings toward the United States shifted based on whether the US had troops fighting in that specific country.
Imagine you're at a neighborhood meeting where people from different blocks complain about local issues. Even though they mention different problems, they all sound equally angry and upset. In this paper, YouTube comments from various countries discuss different political topics, but they share a similar negative emotional tone, showing one regional mood rather than separate ones.
This matters for public diplomacy in the Middle East, as it shows that online emotional expressions are regionally connected rather than nationally divided. Policymakers and observers can better understand shared public sentiment across borders.
The abstract does not detail the exact methods of the sentiment pipeline or discuss if these findings hold for other social media platforms or languages. It is limited to the five countries and specific socio-political topics analyzed, and does not establish causal relationships, only correlations.
Ask anything about this paper. Answers come from its abstract, and say so when the abstract doesn't cover your question.
Affective publics in Arabic YouTube — Lynnette Hui Xian Ng, Craig Douglas Albert, Abdullah Melhem et al.
Abstract licence: CC0
Explanation generated by Synthesis from the abstract — it is not the original paper. This is a preprint, so it hasn't necessarily been peer reviewed.