Golf and GameForge: Innovative Analytics for Recommender Systems; Female Athletes’ Self-Presentation on Instagram

Author:
Kreitzer, Rachel, School of Engineering and Applied Science, University of Virginia
Advisors:
Scherer, William, University of Virginia
Foley, Rider, University of Virginia
Abstract:

College golf recruiting is a tedious and unreliable process that puts immense strain on college coaches and potential recruits. Coaches are forced to spend their time researching and attending many tournaments to get an idea of which players will fit their team and the final recruiting decisions are largely based on gut feeling. Recruits can also be overwhelmed with the array of decisions they have to make when considering which college to play for. The recruiting tool that we are creating will use machine learning techniques to provide coaches with players that would benefit their team and give potential recruits a list of colleges that would be a good fit. Social implications of this tool should be taken into consideration when it could play a major part in a player’s future or a coach’s career. It is essential to acknowledge the potential repercussions of using player data to help guide recruiting decisions.
While the ethical concerns for golf recruiting are worth evaluating, this research will shift to examining the visual depiction of female athletes on social media. In order to assess the impacts of social networks on female athletes, I will be using case studies of popular female athletes on Instagram, a photo-based social media platform. These case studies will be evaluated using the social construction of technology to determine Instagram’s impact on the athletes. By examining the athletes’ images and the public’s response to their posts, my research will evaluate how female athletes choose to portray themselves and how their followers react to different types of images. I will also attempt to understand if comments and reactions to their posts differ based on the type of image they display. I expect that my research will show that the public is more likely to objectify female athletes when the image is outside of an athletic context. I hypothesize that female athletes get more response from their followers, negative or positive, when they post pictures in revealing attire. Because of this theory, I also expect the athletes to share more pictures of themselves outside of an athletic context than in their sports environment to garner more response from followers.

Degree:
BS (Bachelor of Science)
Keywords:
Sports analytics, Female athletes, Goffman's theory of self-presentation, Golf analytics, Predictive analytics, Machine learning
Sponsoring Agency:
GameForge Golf
Notes:

School of Engineering and Applied Science
Bachelor of Science in Systems Engineering
Technical Advisor: William Scherer
STS Advisor: Rider Foley
Technical Team Members: Rose Dennis, Zachary Kay, Jerry Lu, Sam Roberts, Thomas Twomey, Steven Wasserman

Language:
English
Issued Date:
2022/05/08