Using Autoencoders for Anomaly and Drift Detection in Linguistic Segmentation on Product Review Platforms and Recommendation Systems

Product review platforms are vital for the consumer technology and digital commerce ecosystem, offering insights into buying preferences, satisfaction levels, and trends. They support personalization, product improvements, and inventory management. However, their effectiveness can be undermined by irregularities in data, such as fraudulent reviews and shifts in consumer language.This paper explores the use of autoencoders—an unsupervised learning architecture—for detecting anomalies and concept drift in customer feedback. Building on research in anomaly detection, concept drift adaptation, and autoencoder architecture, we propose a robust framework for accurately identifying anomalies and monitoring drift. Using the Amazon Product Reviews Dataset, we validate our approach, achieving high precision in anomaly detection and reliable drift monitoring over time.We provide visualizations, pseudo-code for reproducibility, and practical deployment suggestions. Our findings demonstrate that combining linguistic segmentation with unsupervised modeling enhances system robustness, ensuring recommendation engines remain trustworthy and relevant amidst evolving language and malicious manipulation.