Predicting the Sentiment Polarity and Rating of Yelp Reviews
This work addresses the need for automated sentiment analysis in online business reviews, but it is incremental as it applies standard machine learning methods to a common dataset.
The paper tackled the problem of predicting sentiment polarity and star ratings from Yelp reviews, achieving 92.90% accuracy for positive/negative classification and 63.92% for 5-star classification using Logistic Regression.
Online reviews of businesses have become increasingly important in recent years, as customers and even competitors use them to judge the quality of a business. Yelp is one of the most popular websites for users to write such reviews, and it would be useful for them to be able to predict the sentiment or even the star rating of a review. In this paper, we develop two classifiers to perform positive/negative classification and 5-star classification. We use Naive Bayes, Support Vector Machines, and Logistic Regression as models, and achieved the best accuracy with Logistic Regression: 92.90% for positive/negative classification, and 63.92% for 5-star classification. These results demonstrate the quality of the Logistic Regression model using only the text of the review, yet there is a promising opportunity for improvement with more data, more features, and perhaps different models.