Predicting a Business Star in Yelp from Its Reviews Text Alone

TL;DR

This paper develops a machine learning approach to predict Yelp business ratings solely from review texts, aiming to provide unbiased overviews and reduce subjectivity in ratings.

Contribution

It introduces a novel combination of feature extraction methods and machine learning models to accurately predict business ratings from review texts.

Findings

Achieved RMSE of 0.6 with Linear Regression using top frequent words or adjectives.

Demonstrated effectiveness of POS-based feature selection in rating prediction.

Provided a method to generate unbiased business ratings from textual reviews.

Abstract

Yelp online reviews are invaluable source of information for users to choose where to visit or what to eat among numerous available options. But due to overwhelming number of reviews, it is almost impossible for users to go through all reviews and find the information they are looking for. To provide a business overview, one solution is to give the business a 1-5 star(s). This rating can be subjective and biased toward users personality. In this paper, we predict a business rating based on user-generated reviews texts alone. This not only provides an overview of plentiful long review texts but also cancels out subjectivity. Selecting the restaurant category from Yelp Dataset Challenge, we use a combination of three feature generation methods as well as four machine learning models to find the best prediction result. Our approach is to create bag of words from the top frequent words in all raw text reviews, or top frequent words/adjectives from results of Part-of-Speech analysis. Our results show Root Mean Square Error (RMSE) of 0.6 for the combination of Linear Regression with either of the top frequent words from raw data or top frequent adjectives after Part-of-Speech (POS).