Subburu Latha¹, S. Vinay2 , G. Chandu3 , K. Ragna4 , Chilupaka Spandhana5 , B. Prathyusha6 03 03 The exponential growth of online review platforms has been paralleled by a surge in fake incentivised and spam reviews fundamentally undermining consumer trust and distorting purchase decisions This paper presents TrustReview a hybrid learning framework for automated detection of fake online reviews that synergises a finetuned RoBERTa transformer backbone with a multimodal feature pipeline encompassing linguistic cues sentiment analysis reviewer behavioural metadata and readability metrics The system is trained on a curated SMOTEbalanced corpus of 21540 reviews drawn from Yelp Amazon and TripAdvisor integrated with the ORCA benchmark dataset TrustReview achieves a classification accuracy of 971 precision of 962 recall of 957 and F1score of 959 significantly outperforming all evaluated baselines including Naive Bayes 714 F1 SVM 775 Random Forest 811 BiLSTM 851 and standalone RoBERTa 897 Deployed as a Flask REST API with subsecond inference latency 074 seconds average TrustReview provides a scalable realtime solution for review authenticity verification across ecommerce and hospitality platforms Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026