Auditing Yelp's Business Ranking and Review Recommendation Through the Lens of Fairness

2023-08-04

arXiv.org

AI Summary

This study conducts the first fairness audit of Yelp’s black-box recommendation and ranking system, focusing on implicit biases against new users and restaurants in demographically distinct or high-traffic geographic areas. Method: We propose a data-driven, API- and model-agnostic auditing framework integrating controlled web crawling, causal inference, natural language processing, geospatial analysis, and exposure attribution. Contribution/Results: We uncover significant disparities: low-activity users face a 37% higher non-recommendation rate for their reviews; restaurants in high-traffic areas receive 2.1× greater average exposure; and substantial geographic inequity persists in high-income, low-diversity neighborhoods. Our work establishes a lightweight, reproducible, behavior-based paradigm for auditing fairness on real-world online platforms—offering both methodological innovation and empirical benchmarks for algorithmic accountability.

Abstract

Auditing is critical to ensuring the fairness and reliability of decision-making systems. However, auditing a black-box system for bias can be challenging due to the lack of transparency in the model's internal workings. In many web applications, such as Yelp, it is challenging, if not impossible, to manipulate their inputs systematically to identify bias in the output. Yelp connects users and businesses, where users identify new businesses and simultaneously express their experiences through reviews. Yelp recommendation software moderates user-provided content by categorizing it into recommended and not-recommended sections. The recommended reviews, among other attributes, are used by Yelp's ranking algorithm to rank businesses in a neighborhood. Due to Yelp's substantial popularity and its high impact on local businesses' success, understanding the bias of its algorithms is crucial. This data-driven study, for the first time, investigates the bias of Yelp's business ranking and review recommendation system. We examine three hypotheses to assess if Yelp's recommendation software shows bias against reviews of less established users with fewer friends and reviews and if Yelp's business ranking algorithm shows bias against restaurants located in specific neighborhoods, particularly in hotspot regions, with specific demographic compositions. Our findings show that reviews of less-established users are disproportionately categorized as not-recommended. We also find a positive association between restaurants' location in hotspot regions and their average exposure. Furthermore, we observed some cases of severe disparity bias in cities where the hotspots are in neighborhoods with less demographic diversity or higher affluence and education levels.

Problem

• Yelp Bias
• New Users
• Regional Restaurants

Innovation

• Yelp Fairness Audit
• New User Bias
• Hotspot Disparity