INTEGRATING DEEP LEARNING FOR AUTOMATED DETECTION OF NEGATIVE HOTEL REVIEWS

This paper presents an automated deep learning framework for detecting and classifying negative hotel reviews, integrating both textual and numerical inputs. The model utilizes a Fully Connected Feedforward Neural Network (FCNN) to capture complex global relationships and non-linear patterns in the data, ensuring accurate classification of negative reviews. Experimental results show that the model achieves an accuracy of 90.1% and precision of 88.6%. These results demonstrate the model's effectiveness in processing large-scale datasets, outperforming traditional methods in terms of classification performance. By automating the detection of negative reviews, our approach offers a scalable solution for the hospitality industry to enhance both operational efficiency and customer satisfaction.