AI Model Combines Text and Images to Detect Fake Reviews with High Accuracy
Published on November 5, 2025 at 05:00 AM
A new artificial intelligence model is making waves in the fight against fake online reviews by combining text and image analysis. Developed by Suhasnadh Reddy Veluru, Sai Teja Erukude, and Viswa Chaitanya Marella, the system uses BERT for textual encoding and ResNet-50 for extracting visual features, fusing these elements to accurately classify review authenticity.
The multimodal approach addresses a critical gap in current detection models, which often rely solely on textual data and fail to recognize inconsistencies between text and accompanying images. The model was trained on a curated dataset of over 20,000 user-uploaded images across various domains, including food delivery, hospitality, and e-commerce.
Experimental results demonstrate the model's superior performance, achieving an F1-score of 0.934 on the test set, significantly outperforming unimodal baselines. This innovation offers a scalable solution for content moderation and aims to safeguard digital trust across online platforms.