Sentiment analysis became a very motivating area in both academic and industrial fields due to the exponential increase of the online published reviews and recommendations. To solve the problem of analysing and classifying those reviews and recommendations, several techniques have been proposed. Lately, deep neural networks showed promising outcomes in sentiment analysis. The growing number of Arab users on the Internet along with the increasing amount of published Arabic reviews and comments encouraged researchers to apply deep learning to analyse them. This article is a comprehensive overview of research works that utilised the deep learning approach for Arabic sentiment analysis.

Automatic image annotation (AIA) has been adopted in different applications such as image retrieval and classification. Deep Learning is used in AIA to extract image features and then convert these features into text descriptions and labels. However, conventional AIA models that employ deep learning methods suffer from various shortcomings, such as poor annotation performance. This work proposes an AIA model based on convolutional neural networks (CNNs), generative adversarial networks (GANs), and transfer learning. GANs have attracted a lot of interest because of its ability to generate data without explicitly using probability density. Thus, it has proven its usefulness in image annotation and image augmentation. In this work, an Auxiliary classifier-GAN (ACGAN) has been used, where the discriminator predicts the class of an image rather than taking it as a given input; therefore, the stabilization of the training stage is ensured, and the generation of high-quality images is provided. Transfer learning is also used to enhance the performance of the classification. The proposed model outperforms the best state-of-the-art models in terms of MiAP, F-measure and error rate using ImageClef, ESPGame and IAPR-TC12 datasets.

As a valuable tool for comprehending the emotions and perspectives of individuals, the significance of sentiment analysis has risen as a result of the growing of user-generated Arabic content online. Aspect-based sentiment analysis (ABSA) has recently gained significant attention and has become one of the most popular research points. The main objective of ABSA is to extract the aspects and identify their corresponding sentiment polarity from a provided review or text. Compared to generic sentiment analysis, the outcome provides more in-depth information. This paper aims to explore the deep learning (DL) methods employed in Arabic ABSA, and provides a new taxonomy that organizes various ABSA studies depending on the number of tasks processed. Additionally, the models proposed for Arabic ABSA and their contributions and limitations are discussed and summarized to identify gaps in the field. Furthermore, Arabic datasets for ABSA are reviewed as well. Specifically, this article analyzes studies published between 2019 and April 2024. In addition to ascertaining potential future directions that would encourage researchers to contribute to Arabic ABSA studies and generate more effective algorithms.

This paper proposes a semantic retrieving method for an image retrieval system that employs the fusion of the textual and visual information of the image dataset which is a recent trend in image retrieval researches. It combines two different data mining techniques to retrieve semantically related images: clustering and association rule mining algorithm. At the offline phase of the method, the association rules are discovered between the text semantic clusters and the visual clusters to use it later in the online phase. To evaluate the proposed system, the experiment was conducted on more than 54,500 images of ImageCLEF 2011 Wikipedia collection. The proposed retrieval system was compared to an online system called MMRetrieval and to the proposed system but without using association rules. The obtained results show that our proposed method achieved the best precision and mean average precision.