"You eat with your eyes first": Optimizing Yelp Image Advertising

TL;DR

This paper investigates how visual features in Yelp images influence business success by classifying images based on star ratings and identifying common properties of highly effective images, using transfer learning and GANs.

Contribution

It introduces a transfer learning classifier for Yelp images to predict star ratings and employs GANs to analyze features of highly effective images, providing insights into visual factors impacting reviews.

Findings

Classifier achieves 90-98% accuracy in star rating prediction.

Images with blue skies, open surroundings, and many windows correlate with higher reviews.

Identifies visual features associated with successful business images.

Abstract

A business's online, photographic representation can play a crucial role in its success or failure. We use Yelp's image dataset and star-based review system as a measurement of an image's effectiveness in promoting a business. After preprocessing the Yelp dataset, we use transfer learning to train a classifier which accepts Yelp images and predicts star-ratings. Additionally, we then train a GAN to qualitatively investigate the common properties of highly effective images. We achieve 90-98% accuracy in classifying simplified star ratings for various image categories and observe that images containing blue skies, open surroundings, and many windows are correlated with higher Yelp reviews.