Participation in social media particularly in urban centers is growing rapidly. Understanding how information in social media can modify public health behaviors and how social media can be mined to make meaningful public health intervention shall be highly useful as social media use expands. The specific focus of this thesis is to describe how social media on Yelp.com can be mined to gain meaningful public health surveillance that is predictive of real world health code violation. The Second aim of this thesis is to survey an urban area with a high concentration of Yelp users to identify how Yelp use and value of information on Yelp can modify the health behavior of restaurant selection and modify odds of food borne illness.
In our analysis of the predictive power of social media data mined from Yelp.com we found that keywords like “vomit” and “DIRTY” were predictive of substandard health code rating (<80) with Odds Ratio of (45.4), and (3.68) respectively. The logistic regression model used had Sensitivity, Specificity, Positive Predictive Value, and Area under the Receiver Operator Curve of .72, .44, .61, and .78 respectively. Our Survey of an urban area with a high concentration of Yelp users found that those Yelp users that valued Yelp’s measurement of quality “Stars” the most had increased odds of reported food borne illness (1.01-2.54). We also found that despite Yelp.com’s “partnership” with public health officials in San Francisco and their agreement to present public health data on Yelp.com only 10% of respondents knew public health data was posted for restaurants on Yelp.com.
Our results show us that knowledge of health code violations like employee hand washing and presence of vermin decreased respondent desire to select restaurant more than knowledge of health code rating. This is important to note as yelp only presents health code ratings along the restaurants on its site. The findings of the analysis conducted in this thesis allow public health officials to improve the effectiveness of surveillance of restaurants for food borne illness risk factors, and improve partnerships with social media companies like yelp.com to better communicate public health findings and change public health behaviors.
Some files may require a special program or browser plug-in. More Information
|Commitee:||Delfino, Ralph, Hayes, Gillian|
|School:||University of California, Irvine|
|School Location:||United States -- California|
|Source:||MAI 55/01M(E), Masters Abstracts International|
|Keywords:||Foodborne illness, Health behaviors, Health inspection, Public health, Social media, Surveillance|
Copyright in each Dissertation and Thesis is retained by the author. All Rights Reserved
The supplemental file or files you are about to download were provided to ProQuest by the author as part of a
dissertation or thesis. The supplemental files are provided "AS IS" without warranty. ProQuest is not responsible for the
content, format or impact on the supplemental file(s) on our system. in some cases, the file type may be unknown or
may be a .exe file. We recommend caution as you open such files.
Copyright of the original materials contained in the supplemental file is retained by the author and your access to the
supplemental files is subject to the ProQuest Terms and Conditions of use.
Depending on the size of the file(s) you are downloading, the system may take some time to download them. Please be