Arabic tweeps dialect prediction based on machine learning approach

Khaled Alrifai (Higher Institute for Applied Sciences and Technology)
Ghaida Rebdawi (Higher Institute for Applied Sciences and Technology)
Nada Ghneim (Higher Institute for Applied Sciences and Technology)

International Journal of Electrical and Computer Engineering
Vol 11, No 2: April 2021

In this paper, we present our approach for profiling Arabic authors on twitter, based on their tweets. We consider here the dialect of an Arabic author as an important trait to be predicted. For this purpose, many indicators, feature vectors and machine learning-based classifiers were implemented. The results of these classifiers were compared to find out the best dialect prediction model. The best dialect prediction model was obtained using random forest classifier with full forms and their stems as feature vector.