Abstract

The purpose of this project is to explore the field of machine learning and to utilize ML techniques to create a program designed to produce sentences containing a desired word, given by a user. The sentences are to mimic the style and content of the data being used to aid the user in their creative writing process. Machine learning is gaining a lot of attention in the tech world, as buzz words like ``AI'' and ``deep learning'' are seen tacked onto any and everything. Big tech companies are starting to invest a lot of time, money, and resources in machine learning research and AI implementation into their products. The goal of investing in this field is to improve the user experience by programming a computer to think like a human in order to speed up a given task. This can be seen in text prediction, search engine results, and self-driving features in newer vehicles. Using existing myths as training data, this study explores the viability of machine learning in creative disciplines, more specifically, in creative writing. The resulting generated myth-focused sentences will be analyzed against the criteria of what makes up a myth to determine if computers can replicate the same authentic and creative works written by human authors.

Advisor

Sommer, Nathan

Department

Computer Science

Disciplines

Artificial Intelligence and Robotics

Keywords

AI, machine learning, myth, text generation, Markov chains, Writer's Block

Publication Date

2019

Degree Granted

Bachelor of Arts

Document Type

Senior Independent Study Thesis

Share

COinS
 

© Copyright 2019 Scott Stoudt