With the rapid advancement of information technology, online information has been exponentially growing day by day, especially in the form of text documents such as news events, company reports, reviews on products, stocks-related reports, medical reports, tweets, and so on. Due to this, online monitoring and text mining has become a prominent task. During the past decade, significant efforts have been made on mining text documents using machine and deep learning models such as supervised, semisupervised, and unsupervised. Our area of the discussion covers state-of-the-art learning models for text mining or solving various challenging NLP (natural language processing) problems using the classification of texts. This paper summarizes several machine learning and deep learning algorithms used in text classification with their advantages and shortcomings. This paper would also help the readers understand various subtasks, along with old and recent literature, required during the process of text classification. We believe that readers would be able to find scope for further improvements in the area of text classification or to propose new techniques of text classification applicable in any domain of their interest.

In recent years, recommendation systems have gained popularity in the financial services industry. These systems offer personalized recommendations to consumers based on their distinct preferences, behaviors, and historical data. Centralized data storage and processing used in traditional recommendation systems can raise privacy and security concerns. In light of these challenges, in this paper, a federated learning-empowered recommendation model (FLRM) is proposed that utilizes federated learning and blockchain technology. In our proposed model, the central server coordinates model aggregation and communicates with the blockchain network. In FLRM, financial institutions hold their data in private blockchains while participating in the federated learning process. Federated learning provides a solution to these challenges by enabling privacy-preserving collaborative model training across multiple distributed data sources. Blockchain technology enhances the security and transparency of the federated learning model by providing a decentralized and tamper-proof mechanism for data storage and management. By decentralizing the recommendation system, FLRM enhances user privacy, reduces data transfer overhead, and builds trust through transparency. The integration of smart contracts in this proposed model facilitates secure and automated transactions. The proposed approach represents a significant step forward in creating a more secure, privacy-preserving, and effective recommendation system model.

Blockchain technology has the potential to revolutionize the way Intelligent Transportation Systems (ITS) operate in smart cities. By providing a secure and decentralized platform for data exchange and storage, blockchain can enhance the security, privacy, and interoperability of ITS systems. Blockchain technology can be used for various applications in ITS, including secure data exchange between vehicles, infrastructure, and service providers, smart contracts for autonomous vehicles, and decentralized marketplaces for transportation services. However, implementing blockchain in ITS comes with its own set of challenges, including scalability and high computational power requirements. Despite the challenges, blockchain technology offers significant opportunities for ITS in smart cities, enabling new business models and promoting innovation in transportation services. In this paper, we study existing challenges, applications, and future requirements for ITS. We discuss the challenges of the ITS and their impact on smart cities. Blockchain-enabled applications are provided with performance analysis based on the critical parameters of ITS. We also derive the security requirements for future ITS. Finally, we provide some opportunities and possible research areas within the ITS to develop smart cities.

The Internet of things (IoT) is a heterogeneous network of different types of wireless networks such as wireless sensor networks (WSNs), ZigBee, Wi-Fi, mobile ad hoc networks (MANETs), and RFID. To make IoT a reality for smart environment, more attractive to end users, and economically successful, it must be compatible with WSNs and MANETs. In light of this, the present paper discusses a novel quantitative trust model for an IoT-MANET. The proposed trust model combines both direct and indirect trust opinion in order to calculate the final trust value for a node. A Beta probabilistic distribution is used to combine different trust evidences and direct trust has been calculated. The theory of ARMA/GARCH has been used to combine the recommendation trust evidences and predict the resultant trust value of each node in multi-step ahead. Further, a routing protocol has been designed to ensure the secure and reliable end-to-end delivery of packets by only considering trustworthy nodes in the path. Simulation results show that our proposed trust model outperforms similar existing trust models.