The use of pick-up points by consumers is one of the most developed areas of research in the literature on last-mile logistics over the last decade. In this regard, several researchers have attempted to expose the factors that influence consumers’ online shopping behavior and their willingness to use pick-up points. However, no study has addressed this issue in African countries. The aim of this research is to examine the online shopping behavior of Moroccan consumers, focusing on their opinions about using pick-up points to receive/return goods purchased online. This research adopted a qualitative approach through focus group sessions with Moroccan consumers. The results indicate that temporal and spatial flexibility, competitive prices, and the quality of the retailer’s website are the main factors encouraging consumers to buy online. On the other hand, product risk, delivery risk, privacy, and security were identified as the factors that prevent consumers from buying online. In contrast, the location, density, security, and opening hours of pick-up points were considered to be the factors that influence the Moroccan consumer’s choice to use this delivery option when buying online. These findings are important both for parcel delivery companies that want to establish pick-up point networks in Casablanca and for public authorities and local communities that want to formulate policies and implement strategies leading to more sustainable urban environments.

The field of law in Morocco is behind on progress to other fields, where the archiving of legal documents is done manually and the access to the information is increasingly complex. In the scope of this work, we investigate the application of text classification methods to support law professionals, by proposing a system able to automatically select the class of a judgement. We will build four models which are Naïve Bayes, K-Nearest Neighbor, Support Vector Machine and Decision Tree to classify Arabic legal documents, which are tried by the Moroccan court.

Conventional traffic light control systems often exhibit rigid timing patterns, limited flexibility, and insufficient adaptability to changing traffic conditions. This paper specifically addresses the challenges of urban traffic management, addressing researchers and professionals in traffic engineering and intelligent transportation systems. To overcome these challenges, this paper presents an innovative traffic light control method, integrating a CNN-LSTM model for traffic state prediction, combined with a Proximal Policy Optimization (PPO) algorithm for traffic light control decision-making. The model is based on a representation of intersection states through key indicators (such as active green phase, congestion levels, congestion variations, and vehicle speeds) and employs deep reinforcement learning to optimize traffic light control strategies. The adopted method is compared with fixed traffic light control approaches and a reinforcement learning (Q-learning) approach in a simulated environment using SUMO. The simulations are based on various traffic scenarios and realistic parameters to maximize the validity of the results. The experimental results indicate that traffic efficiency is significantly improved by up to 92% (for the North-South scenario), while congestion indicators are decreased. These results illustrate the effectiveness of integrating spatiotemporal prediction and PPO-based control for dynamic and adaptive traffic management in urban networks.

Jurisprudence involves studying, interpreting, and applying the law to comprehend its societal impact. Judges annually review cases to ensure accurate law application, which raises privacy concerns when accessing files from other courts. While the legal field has garnered interest from the research community, the challenge of masking personal data, particularly in the Arabic language with limited resources, remains in its early stages. To address this research gap, we develop a two-component system for generating anonymous Arabic judgments. The first component, a personal data extractor model, utilizes Named Entity Recognition (NER) to identify key individual entities like names, addresses, birthdays, case numbers, and national identity codes. We train this model on a purpose-built Arabic legal corpus. The second component involves a Python module designed to mask the personal entities extracted by the first component. Together, these components enable the generation of anonymous judgments. Our model achieves an F1-score of 96.14% when detecting entities in the created Arabic Legal corpus. Additionally, experiments on the ANERCorp corpus, with training and testing splits of 70%-30% and 90%-10%, yield F1-scores of 93.78% and 95.77%, respectively. With these results, our proposed system demonstrates the promising potential for generating anonymous Arabic judgments. Furthermore, the built Arabic legal corpus provides a valuable resource for researchers aiming to enhance domain-specific NER models in Arabic text.

With the growing prevalence of Arabic texts, extracting relevant information from these sources has become increasingly vital. Consequently, there is a pressing demand for technologies and tools capable of processing this relevant data. Named Entity Recognition (NER) is a fundamental technique in the field of information extraction, serving as the basis for many natural language applications such as question-answering (QA), machine translation, and text summarization. This paper presents a detailed review of the evolution of Arabic NER. We begin by providing an in-depth exploration of the foundational aspects of Arabic NER, encompassing its domains, types, applications, annotation schemes, and the challenges inherent in its development. We present an overview of the existing resources applicable to Arabic NER, including datasets, gazetteers, and prevalent processing tools. Then, we classify current approaches into three main paradigms: Rule-Based, Machine Learning (ML), and Deep-Learning (DL) methods. Within each paradigm, we survey notable methods and elucidate their architectures. Additionally, we synthesize the practical applications of these NER methods and propose potential directions for future research in the domain of Arabic NER. This literature review provides a valuable resource for researchers aiming to improve NER studies in Arabic.