Logo Lanfrica

Linguistic Divergence in the Saudi Digital Sphere: Assessing NLP Approaches to Lexical Patterns on TikTok and Public Attitudes on X

Domaine:

natural language processing

Type de record:

dataset
Créateur:
Ala
Éditeur:
Zenodo
Hôte:avatar

This dataset accompanies a study of English–Arabic code-mixing in Saudi digital discourse on TikTok and X. It includes cleaned TikTok comment data, lexical classification and code-mixing analysis outputs, English and Arabicized-English word lists used in the analysis, automated sentiment-analysis results for X comments, manual sentiment classifications, and the Python code used for data cleaning.

Languages

Similaires