Using Text Analysis to Target Government Inspections: Evidence from Restaurant Hygiene Inspections and Online Reviews

  title={Using Text Analysis to Target Government Inspections: Evidence from Restaurant Hygiene Inspections and Online Reviews},
  author={Jun Seok Kang and Polina Kuznetsova and Yejin Choi and Michael Luca},
Restaurant hygiene inspections are often cited as a success story of public disclosure. Hygiene grades influence customer decisions and serve as an accountability system for restaurants. However, cities (which are responsible for inspections) have limited resources to dispatch inspectors, which in turn limits the number of inspections that can be performed. We argue that NLP can be used to improve the effectiveness of inspections by allowing cities to target restaurants that are most likely to… 

Figures and Tables from this paper

Digitizing Disclosure: The Case of Restaurant Hygiene Grades

The initial results show that there is a strong correlation between Yelp ratings and hygiene grades, and thus far, there is little customer response to the hygiene grades.

Dynamic Restaurants Quality Mapping Using Online User Reviews

OGRs were found to provide valid indicators of restaurant quality based on inspection ratings and can thus contribute to the prevention of foodborne illness among citizens in real time and be incorporated in restaurant management dashboards.

Digitizing Disclosure: The Case of Restaurant Hygiene Scores

It is found score posting is effective, but improving salience further increases consumer response, and a two-stage intervention is implemented that separately identifies consumer response to information disclosure and a disclosure design with improved salience—a consumer alert.

Predicting Food Safety Compliance for Informed Food Outlet Inspections: A Machine Learning Approach

This work capitalizes on the theory that food outlet compliance is a function of its geographic context, namely the characteristics of the neighborhood within which it sits to make robust predictions of compliance for newly opened businesses and those awaiting repeat inspections.

The challenges of food law enforcement : perceptions of environmental health practitioners in the Northwest of England

In the United Kingdom (UK) food law and its enforcement are currently governed by European and domestic law through a regulatory framework that seeks to provide a high level of public health

Identifying Methods for Monitoring Foodborne Illness: Review of Existing Public Health Surveillance Techniques

By analyzing studies in digital epidemiology, computer science, and public health, this paper has identified and analyzed methods of disease monitoring that can be transferred to foodborne disease surveillance.



The Effect of Information on Product Quality: Evidence from Restaurant Hygiene Grade Cards

It is shown that the introduction of hygiene quality grade cards in 1998 causes restaurant health inspection scores to increase, consumer demand to become sensitive to changes in restaurants' hygiene quality, and the number of foodborne illness hospitalizations to decrease.

The use of restaurant inspection disclosure systems as a means of communicating food safety information

The World Health Organization estimates that up to 30% of individuals in developed countries become ill from food or water each year. Up to 70% of these illnesses are estimated to be linked to food

The Case in Support of Restaurant Hygiene Grade Cards

Study of restaurant hygiene and the role played by health inspections in Los Angeles County over a three-year period indicates that restaurant hygiene regulations and inspections are a fairly imperfect device for assuring good-quality hygiene.


This paper explores the ways in which consumers assess the safety of food in restaurants and other eating-out establishments, and the resulting impact on restaurant choice. The analysis builds on the

Reputational Incentives for Restaurant Hygiene

How can consumers be assured that firms will endeavor to provide good quality when quality is unobservable prior to purchase? We test the hypothesis that reputational incentives are effective at

Distributional Footprints of Deceptive Product Reviews

A range of experiments confirm the hypothesized connection between the distributional anomaly and deceptive reviews and provide novel quantitative insights into the characteristics of natural distributions of opinions in the TripAdvisor hotel review and the Amazon product review domains.

Finding Deceptive Opinion Spam by Any Stretch of the Imagination

This work develops and compares three approaches to detecting deceptive opinion spam, and develops a classifier that is nearly 90% accurate on the authors' gold-standard opinion spam dataset, and reveals a relationship between deceptive opinions and imaginative writing.

Overcoming the J-shaped distribution of product reviews

The existence of a J-shaped distribution is demonstrated, sources of bias that cause this distribution are identified, ways to overcome these biases are proposed, and it is shown that overcoming these biases helps product review systems better predict future product sales.

Predicting Disease Transmission from Geo-Tagged Micro-Blog Data

A probabilistic model is constructed that can predict if and when an individual will fall ill with high precision and good recall on the basis of his social ties and co-locations with other people, as revealed by their Twitter posts, which provides a foundation for research on fundamental questions of public health.

Twitter Catches The Flu: Detecting Influenza Epidemics using Twitter

It is described that Twitter texts reflect the real world, and that NLP techniques can be applied to extract only tweets that contain useful information.