Analysis of Yelp Reviews

Abstract

In the era of Big Data and Social Computing, the role of customer reviews and ratings can be instrumental in predicting the success and sustainability of businesses. In this paper, we show that, despite the apparent subjectivity of user ratings, there are also external, or objective factors which help to determine the outcome of a business's reviews. The current model for social business review sites, such as Yelp, allows data (reviews, ratings) to be compiled concurrently, which introduces a bias to participants (Yelp Users). Our work examines Yelp Reviews for businesses in and around college towns. We demonstrate that an Observer Effect causes data to behave cyclically: rising and falling as momentum (quantified in user ratings) shifts for businesses.