The accelerated development of e-commerce has given rise to sophisticated systems defined by significant user interaction, a variety of product offerings, and considerable quantities of structured and unstructured data. Upholding trust and operational security is becoming ever more essential. E-commerce platforms are susceptible to deceptive practices, including counterfeit reviews, dubious transactions, and anomalous usage behaviors. This research introduces a framework for anomaly detection powered by artificial intelligence, integrating deep learning and natural language processing (NLP) with the isolation forest algorithm tree to enhance the identification of unusual activities on e-commerce platforms. We leveraged customer feedback, transaction logs, and user interaction data obtained from Kaggle. Textual reviews were interpreted using natural language processing (NLP), while deep learning was utilized to discern behavioral patterns. The isolation forest algorithm tree was employed to detect statistical anomalies in multidimensional data. The hybrid model surpassed conventional techniques in terms of detection accuracy, recall, and interpretability. It successfully detects suspicious actions and clarifies anomalies in their relevant context. The application of AI techniques, particularly natural language processing, deep learning, and isolation forest algorithm trees, establishes a solid foundation for anomaly detection in the realm of e-commerce. This approach fosters a more secure and trustworthy experience for online consumers.

Road dust should be considered as a secondary source of contamination in the environment, especially when re-suspended. In our study road dust samples were collected from 8 high-capacity urban roads in two districts of Kraków (Krowodrza and Nowa Huta). Total concentration of toxic elements, such as Cd, Cr, Cu, Mn, Zn, Co, Pb, Ni, Ba and Se were determined using ICP –MS ELAN 6100 Perkin Elmer. A fractionation study were performed using VI step sequential extraction, according to the modified method provided by Salomons and Fӧrstner. Appropriate quality control was ensured by using reagent blanks and analysing certified reference material BCR 723 and SRM 1848a. Concentration of metals in the road dust varied as follows [mg/kg]: Cd 1.02-1.78, Cr 34.4-90.3, Cu 65-224, Mn 232-760, Zn 261-365, Co 4.32-6.46, Pb 85.6-132, Ni 32.2-43.9, Ba 98.9-104 and Se 78.3-132. Degree of contamination of road dust from Nowa Huta was very high (Cdeg 54) and considerable for road dust from Krowodrza (Cdeg 25). Results revealed that road dust samples were heavily contaminated with Cd, Cu, Zn, Mn, Co, Pb, Ni, Ba and Se, in amounts exceeding multiple times geochemical background values. The chemical speciation study using VI step sequential extraction, followed by assessing risk assessment code (RAC) revealed that elements in road dust are mostly bound with mobile and easy bioavailable fractions such as carbonates and exchangeable cations, with the exception for Cr and Cu being mostly associated and fixed with residual and organic matter fraction.