Designing an Efficient Restaurant Recommendation System Based on Customer Review Comments by Augmenting Hybrid Filtering Techniques

Abstract

Recommendation systems are being widely employed in order to provide users with a tailored set of services. They are primarily designed to generate advice or ideas (like restaurants, tourist places, medicines, movies, etc.) that address user concerns and can be efficiently utilized in a variety of industries. In today’s world, where we have a plethora of dining options available, choosing the right restaurant that matches our preferences can be a daunting task. To simplify this process and provide personalized recommendations, restaurant recommendation systems have emerged as a valuable tool. By leveraging the power of natural language processing (NLP), these systems can analyze textual data, such as user reviews and restaurant descriptions, to generate tailored suggestions for users. NLP is one of the machine learning techniques for intelligently and effectively analyzing, comprehending, and extracting meaning from human language. By utilizing techniques like sentiment analysis and named entity recognition, the system can understand user queries and match them with relevant restaurant attributes. It can consider factors such as cuisine type, price range, location, ambiance, and customer reviews to generate accurate and relevant recommendations. In the current study, the evaluation’s findings reveal that the suggested ExtraTreeRegressor algorithm outperforms other algorithms in terms of performance. The novelty of this research lies in the fact that here hybrid filtering is employed, which is not yet implemented in similar studies. The goal of this research article is to provide a more accurate and reachable list of suggested eateries. The results and conclusion show that the suggested approach produces good accuracy.