Purpose: This paper aims to propose a novel way of using textual clustering as a feature selection method. It is applied to identify the most important keywords in the profile classification. The method is demonstrated through the problem of sick-leave promoters on Twitter. Design/methodology/approach: Four machine learning classifiers were used on a total of 35,578 tweets posted on Twitter. The data were manually labeled into two categories: promoter and nonpromoter. Classification performance was compared when the proposed clustering feature selection approach and the standard feature selection were applied. Findings: Radom forest achieved the highest accuracy of 95.91% higher than similar work compared. Furthermore, using clustering as a feature selection method improved the Sensitivity of the model from 73.83% to 98.79%. Sensitivity (recall) is the most important measure of classifier performance when detecting promoters’ accounts that have spam-like behavior. Research limitations/implications: The method applied is novel, more testing is needed in other datasets before generalizing its results. Practical implications: The model applied can be used by Saudi authorities to report on the accounts that sell sick-leaves online. Originality/value: The research is proposing a new way textual clustering can be used in feature selection.

Data preprocessing moves the data from raw to ready for analysis. Data resulting from fraud compromises the quality of the data and the resulting analysis. It can exist in datasets such that it goes undetected since it is included in the analysis. This study proposed a process for measuring the effect of fraudulent data during data preparation and its possible influence on quality. The five-step process begins with identifying the business rules related to the business process(s) affected by fraud and their associated quality dimensions. This is followed by measuring the business rules in the specified timeframe, detecting fraudulent data, cleaning them, and measuring their quality after cleaning. The process was implemented in the case of occupational fraud within a hospital context and the illegal issuance of underserved sick leave. The aim of the application is to identify the quality dimensions that are influenced by the injected fraudulent data and how these dimensions are affected. This study agrees with the existing literature and confirms its effects on timeliness, coherence, believability, and interpretability. However, this did not show any effect on consistency. Further studies are needed to arrive at a generalizable list of the quality dimensions that fraud can affect.

Gate security systems use authentication methods to operate hardware components that grant or deny access to restricted areas. Each context has specific requirements to determine user admissibility. There are currently no design recommendations available for these systems despite their significance. Most research proposes designs based on their recommended authentication scheme without providing general guidance on constructing these systems. This study follows Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and conducts a systematic literature review, combining recent research on smart gates. Studies published between 2016 and 2023 are analyzed and evaluated to identify their main components and authentication schemes. A total of 52 research papers published in various journals and conferences were collected. After conducting the review, three main design themes were identified: smartphones, tags, and biometrics. These themes were the focal point of the study. Out of all the designs, 66% only consider using one-factor authentication. These designs primarily rely on biometric-based methods. During the COVID-19 crisis, some designs used biometric authorization instead of identity authentication to incorporate health status. The focus was detecting whether the person wore a face mask and had a normal body temperature. Furthermore, the review reveals that most studies disregard the system’s hardware components and focus on authorization. Also, only 25% of the studies have conducted an implementation for their design and produced results evaluating their performance. The study concludes that a successful smart gate design must consider and balance cost, usability, and security. Furthermore, health status needs to be verified as an additional layer of protection after determining existing authentication requirements.

This study presents the development and evaluation of Health-Aware Smart Gates (HASG), designed to enhance public health security during the COVID-19 pandemic. When compared with traditional smart gate systems, HASGs offer improved security through rigorous health protocol enforcement, enhanced user experience by reducing wait times, and increased reliability. The innovation lies in its stateful authentication mechanism—a contrast to the conventional stateless systems—which reduces wait times by 31.7% for users re-entering on the same day, significantly enhancing efficiency and security. This server-inspired approach allows HASGs to quickly adapt to various health emergencies and incorporate potential hardware upgrades, further reducing response times and elevating the technology’s contribution to smart gate applications. Prototype testing confirms the system’s high accuracy and reliability, underlining its value in smart gate technology.