Arabic is one of the official languages recognized by the United Nations (UN) and is widely used in the middle east, and parts of Asia, Africa, and other countries. Social media activity currently dominates the textual communication on the Internet and potentially represents people’s views about specific issues. Opinion mining is an important task for understanding public opinion polarity towards an issue. Understanding public opinion leads to better decisions in many fields, such as public services and business. Language background plays a vital role in understanding opinion polarity. Variation is not only due to the vocabulary but also cultural background. The sentence is a time series signal; therefore, sequence gives a significant correlation to the meaning of the text. A recurrent neural network (RNN) is a variant of deep learning where the sequence is considered. Long short-term memory (LSTM) is an implementation of RNN with a particular gate to keep or ignore specific word signals during a sequence of inputs. Text is unstructured data, and it cannot be processed further by a machine unless an algorithm transforms the representation into a readable machine learning format as a vector of numerical values. Transformation algorithms range from the Term Frequency–Inverse Document Frequency (TF-IDF) transform to advanced word embedding. Word embedding methods include GloVe, word2vec, BERT, and fastText. This research experimented with those algorithms to perform vector transformation of the Arabic text dataset. This study implements and compares the GloVe and fastText word embedding algorithms and long short-term memory (LSTM) implemented in single-, double-, and triple-layer architectures. Finally, this research compares their accuracy for opinion mining on an Arabic dataset. It evaluates the proposed algorithm with the ASAD dataset of 55,000 annotated tweets in three classes. The dataset was augmented to achieve equal proportions of positive, negative, and neutral classes. According to the evaluation results, the triple-layer LSTM with fastText word embedding achieved the best testing accuracy, at 90.9%, surpassing all other experimental scenarios.

Internet users are continually exposed to phishing as cybercrime in the 21st century. The objective of phishing is to obtain sensitive information by deceiving a target and using the information for financial gain. The information may include a login detail, password, date of birth, credit card number, bank account number, and family-related information. To acquire these details, users will be directed to fill out the information on false websites based on information from emails, adverts, text messages, or website pop-ups. Examining the website’s URL address is one method for avoiding this type of deception. Identifying the features of a phishing website URL takes specialized knowledge and investigation. Machine learning is one method that uses existing data to teach machines to distinguish between legal and phishing website URLs. In this work, we proposed a method that combines correlation and recursive feature elimination to determine which URL characteristics are useful for identifying phishing websites by gradually decreasing the number of features while maintaining accuracy value. In this paper, we use two datasets that contain 48 and 87 features. The first scenario combines power predictive score correlation and recursive feature elimination; the second scenario is the maximal information coefficient correlation and recursive feature elimination. The third scenario combines spearman correlation and recursive feature elimination. All three scenarios from the combined findings of the proposed methodologies achieve a high level of accuracy even with the smallest feature subset. For dataset 1, the accuracy value for the 10 features result is 97.06%, and for dataset 2 the accuracy value is 95.88% for 10 features.

The social web provides a facility for common people to share their views, comments, feedback, and experiences on various social media platforms. Due to these platforms now communication has become easier and it has provided us with opportunities to use social media channels for various businesses. The survival of an e-commerce business highly relies on customers’ opinions or feedback extensively articulated on internet-based social media platforms or social networking sites. Eventually, analysis of these public opinions from these platforms to identify and demonstrate the cumulative meaningful information is the prime objective of Sentiment Analysis (SA). Summarization of this informative knowledge is advantageous for companies, organizations, and industrialist analysts to improve the quality of their products or services. In this scenario, Aspect-Based Sentiment Analysis (ABSA) has proven to be a powerful companion for companies, organizations, and producers to specify the consumers’ attitudes and opinions towards products and brands’ impressive features. Various efforts have contributed to aspect extraction and sentiment classification over the last few decades. In this review study, we first focus on two diverse research tasks, aspect extraction, and aspect sentiment analysis and then we present a comprehensive review of existing studies in various classifications such as lexicon-based, graph data, topic models, machine learning, and deep learning. This diverse analysis provides pros and cons for various research approaches and comparative analysis. We also discuss various sources and details of datasets, which are used in this research study. We also present the research gaps including open research challenges as a guide for future researchers in the form of future research. Moreover, we also present the bibliometric analysis of the aspect-based sentiment analysis.

Effective security support still remains a challenge even for a standardized Internet of Things network protocol such as the IPv6 Routing Protocol for Low-Power and Lossy Networks (RPL). It provides limited protection against external security attacks but stays highly vulnerable to internal routing attacks. The inherent RPL design of RPL, particularly its topology establishment and maintenance mechanism, makes it easy to initiate such kinds of attacks which target overall network performance and topology stability. Establishing a firm and practical understanding of the impacts of these attacks on RPL networks is still critically needed for further investigation. This is more demanding when considering varying-scale RPL deployments targeted by complex attack scenarios. In this research work, an extensive experimental study of these critical RPL routing attacks considering simple-to-complex attack scenarios in varying-scale RPL network setups is presented. It provides a practical contribution toward experimentally understanding the effectiveness of internal routing attacks when targeting RPL-based IoT networks. The main objective is to provide future research works with a practical reference to the effectiveness of these security attacks and the overall performance of RPL networks under routing attacks. The results indicate the adverse impacts of routing attacks on the overall performance of RPL networks. Even in simple attack scenarios, it was found that the attacked networks experienced noticeable degradation in QoS performance and topology stability. In addition, the attacks incurred considerable increases in energy consumption and control traffic overhead. These were more evident in large-scale experimental setups and also under composite and hybrid routing attacks. QoS performance and topology stability degraded by more than 90% whereas energy consumption and network overhead increased by more than 200%.

The increasing relevance and significant acceptance of Wireless Sensor Network (WSN) solutions have aided the creation of smart environments in a multitude of sectors, including the Internet of Things, and offer ubiquitous practical applications. We examine current research trends in WSN using Artificial Intelligence (AI) technologies and the potential application of these methods for WSN improvement in this study. We emphasize the security, fault detection and tolerance, and quality of service (QoS) concerns in WSN, and provide a detailed review of current research that used different AI technologies to satisfy particular WSN objectives from 2010 to 2022. Specifically, this study’s purpose is to give a current review that compares various AI methodologies in order to provide insights for tackling existing WSN difficulties. Furthermore, there has been minimal existing related work concentrating employing AI approaches to solve security, fault detection and tolerance, and quality of service (QoS) concerns associated to WSN, and our goal is to fill the gap in existing studies. The application of AI solutions for WSN is the goal of this work, and we explore all parts of it in order to meet different WSN challenges such as security, fault detection and tolerance, and QoS. This will lead to an increased understanding of current AI applications in the areas of security, fault detection and tolerance, and QoS. Secondly, we present a comprehensive study and analysis of various AI schemes utilized in WSNs, which will aid the researchers in recognizing the most widely used techniques and the merits of employing various AI solutions to tackle WSN-related challenges. Finally, a list of open research issues has been provided, together with considerable bibliographic information, which provides useful recent research trends on the topics and encourages new research directions and possibilities.