A Composite of Design of Collaborative Filtering Models for Stay Recommendation
R. Sivapriyan, D. Santhakumar, Pramod Kumar Naik, E. Afreen Banu, Waleed Sadeq Jaaywel, Hassn Safi · 2024
Analytics and filtering are becoming more and more important in the online retail space to improve consumer experience and guide corporate strategy. The abundance of faked reviews, known as spam, poses a danger to the accuracy of this data as it attempts to sway consumers’ opinions about rival brands and goods. Numerous researches have looked at effective ways to identify spam reviews in order to address this problem; these methods frequently make use of text analysis and artificial intelligence systems. In this paper, we offer a unique approach for filtering of personalized reviews related to hotel industry. Our method shows encouraging results across several performance parameters after thorough testing on a variety of review datasets. We do more than just remove spam from search results; We also provide customers with accurate product information, improving the overall hotel stay experience.