-
About
This project seeks to use NLP methods to answer the following question: Is soccer commentator Ray Hudson a literary genius or a copy-pasting fraud?
-
Ray Hudson: Genius or Fraud?
Introduction If you’ve watched any La Liga matches in the past or have watched some highlights video where a dude goes absolutely nuts over anything Messi does, then you’ve probably watched a soccer game with Ray Hudson commentary. My friend, Dylan, and I have fallen victim to a multitude of Hudson’s commentary tracks, and to…
-
About
YouTubers can typically be analyzed with the fairly straightforward metrics of subscribers, views, and engagement. However, YouTubers directly looking to create recipes are especially interesting as they also want audiences to replicate their recipes and buy their cookbooks. In this project, we ask the question of if we can determine if YouTube recipe creators are…
-
Understanding the Culinary Side of YouTube
Github (Primarily with Brian Cha, and with extraordinarily minimal assistance from Liz Johnson, Marc Rothken, Shreya Dasari) Motivations Recipe content is especially interesting as one of the ultimate goals of the recipe creator is for audiences to replicate their work. This opens up avenues for much interesting inspection of how audiences engage with content creators.…
-
About
With the rise of coronavirus infection rates and social impacts over the recent time period, we investigate whether individuals who upload YouTube videos have artificially/unconsciously created content that trends more towards relative positivity or negativity as infection rates increase and time passes. Is there any relation between sentiment and government action towards virus? Is there…
-
Sentiments of YouTube Videos Over Covid-19
Repository (Code and Data-sets)Covid – 19 Data-set General Overview In this study, we investigate the association between the development of coronavirus and the sentiment score of the top 10 most popular YouTube videos published before and during the coronavirus pandemic. We wanted to see whether popular content creators were publishing more positive videos or…
-
About
The coming-of-age story is a classic archetype that typically features a clearly defined emotional arc for the protagonist. However, can we pick up on this pattern through some natural language processing and neural network techniques? In this project, we use emotional analysis with BERT to try and discern a clear emotional arc for the protagonist…
-
Methods and Results
* This project was done with P-AI, an on-campus AI club. I was the project manager, and also worked with Elena, John, Kelly, and Phoebe. In this project, we trained a neural network for the task of emotional analysis and then set it loose on a collection of first-person coming-of-age texts to see if there…
-
About
This project uses natural language processing and named entity recognition to parse all the names of scientists found in the index and body of physics textbooks and then automatically query their demographic information. We analyze 10 popular intro texts and the entire Pomona curriculum.
-
About
This project seeks to investigate the progression in sentiment of classic science fiction works from ~1900s-2000s. As various global, international, and domestic events occur in points in history, is there an affect on the sentiment of material released by science fiction authors?
Tai Xiang's Random Projects 