الفهرس | Only 14 pages are availabe for public view |
Abstract The rapid development of tools for communication such as social networks, tweeting, and WhatsApp has generated a large mass of necessary textual data. Also, the COVID-19 pandemic has inflamed social networks; hence the automatic analysis of opinions has become paramount. In analyzing the opinions of the Arabic language, a real challenge is encountered, which lies in the use of different dialects (Egyptian, Saudia, Maghrebian, Gulfian, Levantine, Syrian...) The thesis aims to analyze Arabic tweets in terms of positivity, negativity, or neutrality. This thesis is divided into two parts. The first part has combined two categories to analyze the exploration of Arab opinion. The first category contains six basic algorithms for machine learning. The second includes three models of deep learning. In this part, we chose three challenges for datasets that contain multiple dialects (an unofficial language) and a Modern Standard Arabic (MSA) language. Also, the number of tweets is listed as positive, negative, or neutral. The second part of the thesis depends on the mining of Arabic opinions using swarm intelligence techniques. Two algorithms were relied on in this part, namely Harris Hawks Optimizer (HHO) and Marine Predators Algorithm (MPA). HHO technique aims to reveal the nature of opinions in the Arabic language using an algorithm based on swarm intelligence (SI), which is the Harris Hawks algorithm for selecting the most relevant Arabic terms. The second algorithm, MPA, aims. |