Item-based Collaborative Filtering is a common and efficient approach for recommendation problems. In this study, we have investigated the power of deep learning in textual feature extraction and applied this advantage to a high-performance item-based collaborative filtering recommender system. The proposed approach has been experienced on book datasets added by texts collected from famous book review sites. The experiment proves that the proposed model has better performance thanks to the contribution of the new item profile process method based on Deep Learning.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.