Filtering by
- Creators: School of Life Sciences
There is a lot of variation in health outcomes when it comes to individual states in America. Some states, such as Hawaii, have the life expectancy equivalent to that of developed countries, whereas states like Mississippi have the life expectancy equivalent to that of third world countries. This raised the questions of which states are doing well in health and why, and if their health has to do with their performance in the primary, secondary, tertiary, and/or quaternary prevention levels. The purpose of this research was to investigate if there is a correlation between performance in any of the prevention levels and the overall health status of a state, and if there is, which prevention level would be most beneficial for states to prioritize. The hypothesis of this research was: states that prioritized primary and secondary levels of prevention would have better health than states that prioritized tertiary and quaternary levels of prevention, since basic health measures contribute more to health outcomes than advanced medicine. To investigate this question, indicators were chosen to derive the ranking of each state in health and each of the four prevention levels. Six states were then chosen to represent the high, average, and low health statuses respectively. The six states were ranked for all indicators, and the data was analyzed and compared to determine a potential relationship between the prevention level rankings and the overarching health ranking. It was found that there is a correlation between performance in the primary and secondary prevention levels and a state’s overall health status, whereas there was no such correlation for the tertiary and quaternary levels. A model for health was proposed for states looking to improve their health status, which was to invest in primary prevention, followed by secondary, tertiary, then quaternary prevention and only moving to the next prevention level once the previous level reached a satisfactory threshold.
For our thesis, we analyzed a set of data from the on-going longitudinal study, “Aging In the Time of COVID-19” (Guest et al., ongoing) from the Center for Innovation in Healthy and Resilient Aging at Arizona State University. This study researched how COVID-19 and the resulting physical/social distancing impacted aging individuals' health, wellbeing, and quality-of-life. The survey collected data regarding over 1400 participants’ social connections, health, and experiences during COVID-19. This study gathered information about participants’ comorbid conditions, age, sex, location, etc. We presented this work in the form of a website including the traditional elements of an Honors Thesis as well as a visual essay with the data analysis portion coded with the JavaScript library D3 and a list of resources for our target audience, older adults who are experiencing social isolation and/or loneliness.
The e-commerce market utilizes information to target customers and drive business. More and more online services have become available, allowing consumers to make purchases and interact with an online system. For example, Amazon is one of the largest Internet-based retail companies. As people shop through this website, Amazon gathers huge amounts of data on its customers from personal information to shopping history to viewing history. After purchasing a product, the customer may leave reviews and give a rating based on their experience. Performing analytics on all of this data can provide insights into making more informed business and marketing decisions that can lead to business growth and also improve the customer experience.
For this thesis, I have trained binary classification models on a publicly available product review dataset from Amazon to predict whether a review has a positive or negative sentiment. The sentiment analysis process includes analyzing and encoding the human language, then extracting the sentiment from the resulting values. In the business world, sentiment analysis provides value by revealing insights into customer opinions and their behaviors. In this thesis, I will explain how to perform a sentiment analysis and analyze several different machine learning models. The algorithms for which I compared the results are KNN, Logistic Regression, Decision Trees, Random Forest, Naïve Bayes, Linear Support Vector Machines, and Support Vector Machines with an RBF kernel.