چکیده:
Recommender systems are important tools for users to identify their preferred items and for businesses to improve their products and services. In recent years, the use of online services for selection and reservation of hotels have witnessed a booming growth. Customer’ reviews have replaced the word of mouth marketing, but searching hotels based on user priorities is more time-consuming. This study is aimed at designing a recommender system based on the explicit and implicit preferences of the customers in order to increase prediction’s accuracy. In this study, we have combined sentiment analysis with the Collaborative Filtering (CF) based on deep learning for user groups in order to increase system accuracy. The proposed system uses Natural Language Processing (NLP) and supervised classification approach to analyze sentiments and extract implicit features. In order to design the recommender system, the Singular Value Decomposition (SVD) was used to improve scalability. The results show that our proposed method improves CF performance.
خلاصه ماشینی:
A Grouping Hotel Recommender System Based on Deep Learning and Sentiment Analysis Fatemeh Abbasi Postdoctoral researcher, Department of Social and Economic, Alzahra University, Tehran, Iran.
In this study, we have combined sentiment analysis with the Collaborative Filtering (CF) based on deep learning for user groups in order to increase system accuracy.
Nonetheless, the majority of available recommender systems use a simple recommendation provision method that is based on the explicit features of the guests’ profiles such as the users’ rating of the hotels (Gavalas & Kenteris, 2011).
Overview of Collaborative Filtering Techniques (Bokde, Girase, & Mukhopadhyay, 2015) (View the image of this page) In the memory-based approach, the user-items ratings matrix is used.
(2019) offered a recommendation method which was based on three principles: the identification of the references to item features in the users’ reviews, the classification of the sentiment orientations that exist in the reviews, and the use of information related to these features.
Materials and Methods This study focuses on improving the recommender system performance using the results of sentiment analysis of user reviews.
The purpose of this study is the sentiment analysis of user reviews and recommendations based on explicit and implicit feedbacks of the hotel guests.
In order to design the recommender systems, two datasets were used, namely the user ratings that express the guests’ explicit feedback on the hotels, and the sentiment analysis of the users’ reviews that represent the guests’ implicit feedback about 32 hotels in five Iranian cities.
A comparative analysis of recommender systems based on item aspect opinions extracted from user reviews.