Matching Items (331)
Filtering by
- All Subjects: Entrepreneurship
- All Subjects: Machine Learning
- Creators: Barrett, The Honors College
- Status: Published
Description
Background: As the growth of social media platforms continues, the use of the constantly increasing amount of freely available, user-generated data they receive becomes of great importance. One apparent use of this content is public health surveillance; such as for increasing understanding of substance abuse. In this study, Facebook was used to monitor nicotine addiction through the public support groups users can join to aid their quitting process. Objective: The main objective of this project was to gain a better understanding of the mechanisms of nicotine addiction online and provide content analysis of Facebook posts obtained from "quit smoking" support groups. Methods: Using the Facebook Application Programming Interface (API) for Python, a sample of 9,970 posts were collected in October 2015. Information regarding the user's name and the number of likes and comments they received on their post were also included. The posts crawled were then manually classified by one annotator into one of three categories: positive, negative, and neutral. Where positive posts are those that describe current quits, negative posts are those that discuss relapsing, and neutral posts are those that were not be used to train the classifiers, which include posts where users have yet to attempt a quit, ads, random questions, etc. For this project, the performance of two machine learning algorithms on a corpus of manually labeled Facebook posts were compared. The classification goal was to test the plausibility of creating a natural language processing machine learning classifier which could be used to distinguish between relapse (labeled negative) and quitting success (labeled positive) posts from a set of smoking related posts. Results: From the corpus of 9,970 posts that were manually labeled: 6,254 (62.7%) were labeled positive, 1,249 (12.5%) were labeled negative, and 2467 (24.8%) were labeled neutral. Since the posts labeled neutral are those which are irrelevant to the classification task, 7,503 posts were used to train the classifiers: 83.4% positive and 16.6% negative. The SVM classifier was 84.1% accurate and 84.1% precise, had a recall of 1, and an F-score of 0.914. The MNB classifier was 82.8% accurate and 82.8% precise, had a recall of 1, and an F-score of 0.906. Conclusions: From the Facebook surveillance results, a small peak is given into the behavior of those looking to quit smoking. Ultimately, what makes Facebook a great tool for public health surveillance is that it has an extremely large and diverse user base with information that is easily obtainable. This, and the fact that so many people are actually willing to use Facebook support groups to aid their quitting processes demonstrates that it can be used to learn a lot about quitting and smoking behavior.
ContributorsMolina, Daniel Antonio (Author) / Li, Baoxin (Thesis director) / Tian, Qiongjie (Committee member) / School of Mathematical and Statistical Sciences (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Socks + Boxers began as a simple idea on a trip through Victoria's Secret as a solution to the lack of choice in quality and affordable undergarments for men. Currently, there is no central hub for men's socks and underwear. Customers shopping for men's undergarments have few choices currently: purchase an inexpensive, average quality, predetermined pack of Hanes, Fruit of the Loom, or other common undergarment brand from a store like Walmart or Target; shop for individual pieces of expensive designer underwear at a high-end department store such as Nordstrom; or, finally, purchase slightly above average quality, but fairly expensive, brand name undergarments at physical stores such as American Eagle, Urban Outfitters, or Abercrombie & Fitch, or online stores such as MeUndies. Socks + Boxers seeks to combine the accessibility and reliability of common undergarment brands, the quality and luxury-feel of high-end undergarments, and the concept of choice provided by stores that sell men's undergarment lines into a single business. We also plan to tap into the booming subscription services industry and create a way for customers to easily update and replenish their undergarment wardrobe on a regular basis with exactly what they want. In order to start out on the right foot and begin developing this business plan from the ground up, we began researching and developing a Business Model Canvas, a tool that breaks out necessary pieces of a successful business plan into easy to understand blocks. We took a critical look at the problem at hand, its potential solutions, the value the solutions provide, how we plan to start, grow, and nourish our customer base, and much more. The different pieces of this business model puzzle all come together in the following pages.
ContributorsBernat, Johnathon (Co-author) / Braaten, Joshua (Co-author) / Kashiwagi, Dean (Thesis director) / Kashiwagi, Jacob (Committee member) / Department of Finance (Contributor) / Department of Information Systems (Contributor) / School of Accountancy (Contributor) / Barrett, The Honors College (Contributor)
Created2016-05
Description
Africa has some of the "fastest growing economies," yet there is a lack of a middle class (Economist). Natural resources have attracted foreign investments, however, most of the revenue exit these economies. What remains a consistent, permanent advantage is culture; it has been the most integrated core value before and after colonialism. The concept of culture has become a part of the identity of Africa and it has not been leveraged to its full potential. The 2013 Creative Economy Report states, "Culture is a way to create jobs and improve people's lives. It empowers people. It works for development" (UNESCO/UNDP). Cultural industries create local sustainable jobs that are less susceptible to the fluctuation of the global economy compared to jobs in factories and multinational companies. They are based on "local tacit know how" that is not accessible globally as they are people intensive rather than capital intensive (Scott A.J, 1999). Activ8 seeks to tap into this opportunity by maximizing the economic potential of developing economies by investing in their cultural industries. Activ8 aspires to accomplish this by targeting two sets of customers: creators, who are the activators, and investors. Our activators consist of two target segments: one living and working in these industries in a developing country, and the other being refugee clients who may have been exposed to a cultural industry and may want to pursue developing cultural products in their new country of asylum. Our investors are globally minded individuals who want to be culturally aware, have an appreciation for authentic cultural products, or seek to invest in entrepreneurial pursuits in Africa. During our first phase we will focus on the cultural industries in Ghana, West Africa. This will range from products in the textiles industry to sculptures and traditional instruments. We plan to pilot the first phase in Ghana and in the second phase, form a partnership with the International Rescue Committee, a refugee settlement agency, in Arizona. Our goals are to provide education and mentoring, market accessibility, product development, and financing to encourage and empower activators to be self-sufficient and successful cultural entrepreneurs, whiles improving economic development in their communities. Our online store will feature our activators' authentic products, their stories, and the cultural importance of each product. There will also be a platform for entrepreneurs in other industries in Africa to connect with venture capitalists or angel investors around the world. The educational component will be infused with product development and entrepreneurship training derived from the "From AHA!! to EXIT" strategy coined by Aram Chavez from the College of Technology and Innovation at ASU. In order for Activ8 to successfully execute its mission, Activ8 will need to be able to give our team and our activators access to technology, mentorship, and financial resources to operate an online store and rum Activ8's educational program. We also envision creating partnerships with boutiques and retail corporations to adapt these cultural products. Our long-term goal is formulate the conditions conducive for economic growth and sustainable development to ensure Africans become the main agents of development.
ContributorsAdusei, Esther (Author) / Chavez, Aram (Thesis director) / Schoellman, Todd (Committee member) / Department of Supply Chain Management (Contributor) / School of International Letters and Cultures (Contributor) / W. P. Carey School of Business (Contributor) / Department of Finance (Contributor) / Economics Program in CLAS (Contributor) / Barrett, The Honors College (Contributor)
Created2015-12
Description
The purpose of this study is to examine how social connectivity in a collaborative business environment translates to online social communication, namely to social media. Not a lot of academic research focuses in-depth on how startups and entrepreneurs within the technology industry perceive social media, or how their work environment can influence the ways they see the role of these platforms. Gangplank was chosen as the subject of this case study based on the emphasis they as a coworking space put on connecting to others in order to accomplish mutual goals. Initial research showed that entrepreneurs using social media did so with a collaborative focus in mind. However, it was unclear if, by developing their businesses in a space devoted to fostering social relationships, entrepreneurs would be more likely to engage and interact with other users on social media platforms. Furthermore, it was unclear if their attitudes toward online and offline communication would be affected by spending time in a dedicated social workspace. In order to find how some entrepreneurs that started or worked closely in the beginning stages of a collaborative, connection-driven workspace used social media and see whether or not they used the platform to establish and build relationships and connect with others, three entrepreneurs from such a workspace were personally interviewed. In these interviews, each entrepreneur gave their personal feelings and opinions on the space itself, their view on the role of social media, and whether or not they connected their space to their social media use. The study also examined each entrepreneur's social media profile on one prominent social network to see how each was practically using the platform, and to analyze how each entrepreneur's use of the platform compared to his perceptions of social media as a whole. The study found that entrepreneurs who became established in a collaboration-oriented space definitely interacted frequently on social media. Each entrepreneur interviewed expressed the importance of working closely with others and forming valuable connections through both online and offline means. These entrepreneurs were established to have followed all the best practices of social media use outlined through research, and to have had a large number of personally engaging interactions and conversations on observed social media platforms.
ContributorsThompson, Lauren Elizabeth (Author) / Wu, Xu (Thesis director) / Dodge, Nancie (Committee member) / Walter Cronkite School of Journalism and Mass Communication (Contributor) / Barrett, The Honors College (Contributor)
Created2015-12
Description
To investigate the impacts of an energy efficiency retrofit, indoor air quality and resident health were evaluated at a low‐income senior housing apartment complex in Phoenix, Arizona, before and after a green energy building renovation. Indoor and outdoor air quality sampling was carried out simultaneously with a questionnaire to characterize personal habits and general health of residents. Measured indoor formaldehyde levels before the building retrofit routinely exceeded reference exposure limits, but in the long‐term follow‐up sampling, indoor formaldehyde decreased for the entire study population by a statistically significant margin. Indoor PM levels were dominated by fine particles and showed a statistically significant decrease in the long‐term follow‐up sampling within certain resident subpopulations (i.e. residents who report smoking and residents who had lived longer at the apartment complex).
ContributorsFrey, S.E. (Author) / Destaillats, H. (Author) / Cohn, S. (Author) / Ahrentzen, S. (Author) / Fraser, M.P. (Author)
Created2015
Description
Papago Park Outreach is a non-profit organization dedicated towards reducing negative externalities associated with houselessness. Donors can access papagoparkoutreach.org's storefront and purchase items for distribution to the homeless community in Tempe. The items available for purchase and distribution alleviate the burden assumed by public resources, improve unsheltered quality of life and facilitate research on the 'Donation Gap'.
In its first month, Papago Park Outreach received orders for 35 items, which were fulfilled and distributed to unhoused individuals living in Tempe.
ContributorsZehrung, Ashley (Author) / Byrne, Jared (Thesis director) / McCreless, Tam (Committee member) / Barrett, The Honors College (Contributor) / Department of Economics (Contributor)
Created2024-05
Description
Business Design is a thesis project where students can work in groups and consult for various projects. I had the opportunity to work on three major projects for my thesis involving a small entrepreneur looking for a go-to market plan for her board game, an app developer looking for a better way to connect to their target audience, as well as create my own digital product and consulting services that helped founder's lab groups build their online presence through e-commerce. All these projects allowed me to hone my critical thinking skills by working my way through real-life problems that don't have direct answers. I was also able to take away some valuable lessons in leadership and working in a team of very capable students.
ContributorsShosten, Madison (Author) / Akhter, Aliza (Co-author) / Bautista, Hariette (Co-author) / Chou, Chuhhsuan (Co-author) / Guan, Jessica (Co-author) / Flores, Lea (Co-author) / Kim, Min (Co-author) / Qin, Annie (Co-author) / Byrne, Jared (Thesis director) / Lee, Christopher (Committee member) / Barrett, The Honors College (Contributor) / Department of Information Systems (Contributor)
Created2024-05
Description
This thesis project focused on determining the primary causes of flight delays within the United States then building a machine learning model using the collected flight data to determine a more efficient flight route from Phoenix Sky Harbor International Airport in Phoenix, Arizona to Harry Reid International Airport in Las Vegas, Nevada. In collaboration with Honeywell Aerospace as part of the Ira A. Fulton Schools of Engineering Capstone Course, CSE 485 and 486, this project consisted of using open source data from FlightAware and the United States Bureau of Transportation Statistics to identify 5 primary causes of flight delays and determine if any of them could be solved using machine learning.
The machine learning model was a 3-layer Feedforward Neural Network that focused on reducing the impact of Late Arriving Aircraft for the Phoenix to Las Vegas route. Evaluation metrics used to determine the efficiency and success of the model include Mean Squared Error (MSE), Mean Average Error (MAE), and R-Squared Score.
The benefits of this project are wide-ranging, for both consumers and corporations. Consumers will be able to arrive at their destination earlier than expected, which would provide them a better experience with the airline. On the other side, the airline can take credit for the customer's satisfaction, in addition to reducing fuel usage, thus making their flights more environmentally friendly.
This project represents a significant contribution to the field of aviation as it proves that flights can be made more efficient through the usage of open source data.
ContributorsRosenbloom, Yonatan (Author) / Chavez Echeagaray, Maria Elena (Thesis director) / Govindillam, Sreenivasan (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / School of International Letters and Cultures (Contributor)
Created2024-05
An Analysis of the East Valley’s Homeless Services Compared with the Needs of the Unhoused Community
Description
This thesis shows the research results conducted in the East Valley of the Phoenix
Metropolitan Area and the thematic analysis of that data. Data were collected from a
small sample of interviews conducted by the researcher with staff of homeless outreach
organizations and clients of those organizations. A thematic analysis of the interview
data was conducted. The resulting analysis shows that a more significant focus should be
placed on reducing the number of clients in need who decline to use their services by
improving safety, trust, and access to resources and that organizations would benefit
from more consistent funding and a more considerable amount. Finally, as this thesis
shows, both organizations and their clients tend to agree that a lack of access to helpful
resources is a more significant problem than a lack of resources.
ContributorsHults, Clayton (Author) / Kelley, Jason (Thesis director) / Rosales Chavez, Jose-Benito (Committee member) / Barrett, The Honors College (Contributor) / School of Geographical Sciences and Urban Planning (Contributor)
Created2024-05
Description
Manually determining the health of a plant requires time and expertise from a human. Automating this process utilizing machine learning could provide significant benefits to the agricultural field. The detection and classification of health defects in crops by analyzing visual data using computer vision tools can accomplish this. In this paper, the task is completed using two different types of existing machine learning algorithms, ResNet50 and CapsNet, which take images of crops as input and return a classification that denotes the health defect the crop suffers from. Specifically, the models analyze the images to determine if a nutritional deficiency or disease is present and, if so, identify it. The purpose of this project is to apply the proven deep learning architecture, ResNet50, to the data, which serves as a baseline for comparison of performance with the less researched architecture, CapsNet. This comparison highlights differences in the performance of the two architectures when applied to a complex dataset with a multitude of classes. This report details the data pipeline process, including dataset collection and validation, as well as preprocessing and application to the model. Additionally, methods of improving the accuracy of the models are recorded and analyzed to provide further insights into the comparison of the different architectures. The ResNet-50 model achieved an accuracy of 100% after being trained on the nutritional deficiency dataset. It achieved an accuracy of 88.5% on the disease dataset. The CapsNet model achieved an accuracy of 90% on the nutritional deficiency dataset but only 70% on the disease dataset. In comparing the performance of the two models, the ResNet model outperformed the other; however, the CapsNet model shows promise for future implementations. With larger, more complete datasets as well as improvements to the design of capsule networks, they will likely provide exceptional performance for complex image classification tasks.
ContributorsChristner, Drew (Author) / Carter, Lynn (Thesis director) / Ghayekhloo, Samira (Committee member) / Barrett, The Honors College (Contributor) / Computing and Informatics Program (Contributor) / Computer Science and Engineering Program (Contributor)
Created2024-05