Text classifications is the process of categorizing text into organized predefined groups or tags. It is one of the fundamental tasks in most natural language processing systems. Sentiment analysis, topic identification, spam detection, language identification among others are based on automatic text classification techniques. During this workshop, the basic text classification pipeline will be explained in detail along with hand-on experience using Python and Google Colab notebook. The scope of this workshop focuses on Arabic dialectal datasets for text classification. It also includes a project for offensive language detection. Prerequisites: - Basics in Python. - Signed up to Google Colab https://colab.research.google.com/ For any questions, please contact Dr. Fatemah Husain (f.husain@ku.edu.kw).
