Image Source: ALARABIYA NEWS

• This work is done for social computing course project by Sawsan Alowa and Lama AlZahrani.
• The repository contains:
  • Source Code
  • Dataset
  • List of Stop Words (Ref).

The purpose of this project is to study the people percption about COVID-19 vaccine in Saudi Arabia. The dataset was collected using Twitter API over selected days. Also, a set of criteria were applied in the process of collecting the data including user location and language. The cleaning process was performed on the dataset where the following items were removed: emojis, English letters and numbers, special characters, punctuation, diacritics, and tatweel. After that, the data was manually annotated by the authors of the project. Two classification methods were applied, the support vector machine (SVM) and Naive Bayes (NB).