VOX POPULI: THREE ESSAYS ON THE USE OF SOCIAL MEDIA FOR VALUE CREATION IN SERVICES

Prior research shows that electronic word of mouth (eWOM) wields considerable influence over consumer behavior. However, as the volume and variety of eWOM grows, firms are faced with challenges in analyzing and responding to this information. In this dissertation, I argue that to meet the new challenges and opportunities posed by the expansion of eWOM and to more accurately measure its impacts on firms and consumers, we need to revisit our methodologies for extracting insights from eWOM. This dissertation consists of three essays that further our understanding of the value of social media analytics, especially with respect to eWOM. In the first essay, I use machine learning techniques to extract semantic structure from online reviews. These semantic dimensions describe the experiences of consumers in the service industry more accurately than traditional numerical variables. To demonstrate the value of these dimensions, I show that they can be used to substantially improve the accuracy of econometric models of firm survival. In the second essay, I explore the effects on eWOM of online deals, such as those offered by Groupon, the value of which to both consumers and merchants is controversial. Through a combination of Bayesian econometric models and controlled lab experiments, I examine the conditions under which online deals affect online reviews and provide strategies to mitigate the potential negative eWOM effects resulting from online deals. In the third essay, I focus on how eWOM can be incorporated into efforts to reduce foodborne illness, a major public health concern. I demonstrate how machine learning techniques can be used to monitor hygiene in restaurants through crowd-sourced online reviews. I am able to identify instances of moral hazard within the hygiene inspection scheme used in New York City by leveraging a dictionary specifically crafted for this purpose. To the extent that online reviews provide some visibility into the hygiene practices of restaurants, I show how losses from information asymmetry may be partially mitigated in this context. Taken together, this dissertation contributes by revisiting and refining the use of eWOM in the service sector through a combination of machine learning and econometric methodologies.

Fabrication of Poly (D,L-Lactic-Co-Glycolic Acid) Microparticles for Improved Human Papillomavirus Vaccine Delivery

Human papillomavirus (HPV) is the leading cause of cervical cancer and the most prevalent sexually transmitted disease worldwide. HPV vaccines require a multi-dose regimen to provide immunity, contributing to low patient compliance. We addressed this problem by formulating biodegradable poly(D,L-lactic-co-glycolic acid) (PLGA) microparticles and assessing their viability for use in controlled-release vaccines. We hypothesized that we could alter fabrication parameters to produce 1-10 μm microparticles in order to encapsulate ovalbumin (OVA) and HPV virus-like particles (VLPs). Microparticles were fabricated using a double emulsion method and used to elicit an immune response in JAWSII cells. Our results contribute to knowledge of vaccine delivery mechanisms and controlled-release technology, and could contribute to the creation of a viable controlled-release HPV vaccine.

Impact of Cryptosporidium spp. interaction with co-occurring microorganisms on moderate-to-severe diarrhea in the developing world

Diarrheal illness is responsible for over a quarter of all deaths in children under 5 years of age in sub-Saharan Africa and South Asia. Recent findings have identified the parasite Cryptosporidium as a contributor to enteric disease. We examined 9,348 cases and 13,128 controls from the Global Enteric Multicenter Study to assess whether Cryptosporidium interacted with co-occurring pathogens based on adjusted odds of moderate-to-severe diarrhea (MSD). Cryptosporidium was found to interact negatively with Shigella spp., with multiplicative interaction score of 0.16 (95% CI: 0.07 to 0.37, p-value=0.000), and an additive interaction score of -9.81 (95% CI: -13.61 to -6.01, p-value=0.000). Cryptosporidium also interacted negatively with Aeromonas spp., Adenovirus, Norovirus, and Astrovirus with marginal significance. Odds of MSD for Cryptosporidium co-infection with Shigella spp., Aeromonas spp., Adenovirus, Norovirus, or Astrovirus are lower than odds of MSD with either organism alone. This may reduce the efficacy of intervention strategies targeted at Cryptosporidium.