Search In this Thesis
   Search In this Thesis  
العنوان
Deep learning for arabic text sentiment analysis /
الناشر
Rana Mahmoud Kamel Abdelmoneim Kamel ,
المؤلف
Rana Mahmoud Kamel Abdelmoneim Kamel
هيئة الاعداد
باحث / Rana Mahmoud Kamel Abdelmoneim Kamel
مشرف / Mohamed Nafie
مشرف / Karim Seddik
مناقش / Mohamed Khairy
تاريخ النشر
2019
عدد الصفحات
96 P. :
اللغة
الإنجليزية
الدرجة
ماجستير
التخصص
الهندسة (متفرقات)
تاريخ الإجازة
9/12/2019
مكان الإجازة
جامعة القاهرة - كلية الهندسة - Electronics and Communication Engineering
الفهرس
Only 14 pages are availabe for public view

from 113

from 113

Abstract

Nowadays, people express their opinions, reviews on products, movies, hotels{u2026}etc publicly on the internet on social media platforms, blogs or forums. The number of Arabic speaking users on the internet has increased in the last decade and the research for analyzing the Arabic text has gained a lot of attention. In my work, deep learning techniques are used to classify Arabic tweets and reviews into two classes (positive/ negative) and three classes (positive/ negative/ neutral). Also, this work investigates whether deep learning can overcome ordinary machine learning algorithms and replace the effort of feature engineering in previous work. Finally, deep learning proved to have better results than machine learning techniques for most of the used datasets by using a data augmentation architecture