Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 12 of 12
Full-Text Articles in Digital Humanities
Image Generation Through Stylegans: Is It Art?, Sophie Dodd
Image Generation Through Stylegans: Is It Art?, Sophie Dodd
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
I wanted to explore how the role of artificial intelligence is developing within the art world and how current attitudes surrounding AI as a creative tool are changing. I want to experiment with AI generated images using GANs and then seek feedback on them from art and non-art students alike before telling them that they had been generated by an AI. I focused my research on examining the emotional responses people had to AI generated art and the overall question of “can an AI make art?”
Guns In D.C. Appellate Court: Sentiment Analysis On Opinions From The Court Of Appeals For The D.C. Circuit, Grace Peterson, Jon Chun, Katherine Elkins
Guns In D.C. Appellate Court: Sentiment Analysis On Opinions From The Court Of Appeals For The D.C. Circuit, Grace Peterson, Jon Chun, Katherine Elkins
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
No abstract provided.
Creating Art Using Generative Adversarial Networks, Henry Abbott
Creating Art Using Generative Adversarial Networks, Henry Abbott
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
I set out to explore how artificial intelligence generated artwork compares to human created artwork. Using CycleGANs, my goal was to create art, and then conduct a Turing Test in order to determine whether or not one could distinguish between A.I. and human art. Using this test, as well as my own observations, I planned to analyze where CycleGANs succeeds in creating art, as well as where it struggles. Following this analysis, I thought more about what the results mean for art moving forward, and if artificial intelligence can truly create art.
Using Machine Learning To Predict Mlb Success Based On Milb Performance, Alexander Gow
Using Machine Learning To Predict Mlb Success Based On Milb Performance, Alexander Gow
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
In 2017 alone Major League Baseball organizations spent a combined 492 million dollars on acquiring new, young, talented players through the draft or signing international free agents. The effectiveness of an MLB organization’s scouting department is pertinent to ensuring future success. Due to the highly volatile nature of professional sports, identifying a predictive and measurable statistic(s) associated with success among players would be valuable. Furthermore, a team’s ability to quickly and correctly identify players on their Minor League affiliates that will have a positive impact at the Major League level can give them an advantage over other teams. For this …
Analyzing Popular Music Using Spotify’S Machine Learning Audio Features, Noah Amsterdam
Analyzing Popular Music Using Spotify’S Machine Learning Audio Features, Noah Amsterdam
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
The modern ability to stream music using services such as Spotify, Pandora, and Apple music has revolutionized how it is consumed. There is now more music accessible at our fingertips than ever before in history. As someone who has played an instrument their whole life and with some music theory knowledge, I always strive to better understand what I’m listening to. This motivated me to dive into finding out how music is quantified, specifically on Spotify, and what makes up people’s musical taste. I will be approaching music tastes from 3 angles: Spotify, music critics, and my own analysis and …
Generating 3d Sculptures Using A Recurrent Neural Network With Long Short-Term Memory, Nick Downey
Generating 3d Sculptures Using A Recurrent Neural Network With Long Short-Term Memory, Nick Downey
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
Sophisticated generative models have been some of the most obviously impressive achievements of AI in the past decade. Indeed, AI has approached or achieved human-level performance in a variety of domains, with a particular focus placed on artistic disciplines. Because writing a value function for this kind of model is effectively impossible, these models are notoriously difficult to evaluate. My aim was to create such a model, and in doing so elucidate the characteristics of successful generative AI and explore how generative models can be adapted successfully to new domains. And more broadly, I hoped to create a model capable …
Analyzing Visual Sentiment In Photojournalism, Eryn Powell
Analyzing Visual Sentiment In Photojournalism, Eryn Powell
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
Like any other branch of journalism, a photojournalist’s intent is to capture an image that conveys the the events represented in the image while evoking an emotional response that allows the viewer to connect with the content of the photo or news report to which the photo is attached. Under the umbrella of photojournalism, political photography is unique in that it is heavily swayed by public opinion. This project intends to introduce a duel perspective on visual sentiment in political photojournalism.
Lost In Translation: Using Sentiment Analysis To Analyze Translations Of Homer’S Odyssey, Erin Shaheen
Lost In Translation: Using Sentiment Analysis To Analyze Translations Of Homer’S Odyssey, Erin Shaheen
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
For my final project in AI for the Humanities, I knew that I wanted to examine the creative role of translators in classic literature. I ran three different translations of Homer’s The Odyssey through Syuzhet.R, a sentiment analysis tool that has grown increasingly popular in the Digital Humanities field. Syuzhet tracks the emotional arc (also called “emotional valence”) of a text by giving each word a different score. For example, on a scale of -1 to 1, “terrible” might score -1 and “amazing” might score 1. A more neutral word like “okay” would score closer to 0. I chose translations …
Can Gpt-2 Replace A Sex And The City Writers’ Room?, Alasia Destine-Defreece, Samara Handelsman, Talia Light Rake, Ally Merkel, Gracie Moses
Can Gpt-2 Replace A Sex And The City Writers’ Room?, Alasia Destine-Defreece, Samara Handelsman, Talia Light Rake, Ally Merkel, Gracie Moses
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
Someday, in the not-so-distant future, will the writers’ room be replaced by artificial intelligence? This poster was created by a group of actors and writers who were curious about the role artificial intelligence could play in the future of television writing. In the first stage of this project, we prompted GPT-2 with the opening lines of a scene from the television show Sex and the City, and had GPT-2 finish the scene. We filmed the three best GPT-2 generated scenes, and screened these scenes for our “AI for the Humanities” class, along with a filmed version of the original Sex …
Nlp Modeling And Analysis Of Popular Vloggers, Zhaofang (Zach) Wang
Nlp Modeling And Analysis Of Popular Vloggers, Zhaofang (Zach) Wang
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
Vlog, or video blog, is the chicest form of personal production on YouTube First appearing at the beginning of the 21 st century, vlogs saw an enormous rise in popularity around 2005 Differing from other forms of production, vlogs allow their producers more freedom in expressing themselves without the limitation of content, word count, and forms of expression The absence of censorship and early stage marketing allows an almost free market effect in the sense that the most popular vloggers and videos are purely the choice of people Therefore, analyzing viral vlogs and vloggers can offer a more accurate representation …
Doubles And Reflections: Sentiment Analysis And Vladimir Nabokov’S Pale Fire, Catherine Perloff
Doubles And Reflections: Sentiment Analysis And Vladimir Nabokov’S Pale Fire, Catherine Perloff
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
In his novel, Pale Fire, Vladimir Nabokov uses a non-linear narrative composed in three parts: Foreword, Poem, and Commentary, apparently written by two distinct authors, John Shade and Charles Kinbote. Storylines appear to be separate at surface level yet work in interconnected ways at a deeper level. The novel deals with life after death, the story arc of a disguised, exiled king, and provides meta commentary on the art of commentary. The text was tricky to analyze without sentiment analysis principally because of its seemingly disjointed structure. Thus, there’s a bit of irony in that we found a repeated structure …
Topic Modeling Analysis Of Supreme Court Opinions Focusing On Privacy Rights In The Context Of Abortion Law, Ellen Morrissey
Topic Modeling Analysis Of Supreme Court Opinions Focusing On Privacy Rights In The Context Of Abortion Law, Ellen Morrissey
IPHS 300: Artificial Intelligence for the Humanities: Text, Image, and Sound
No abstract provided.