My goal with this project was to just get my feet wet with machine learning. I've been interested
in natural language processing (NLP) for a long time now, so I decided to make a project with it.
So, I looked through kaggle for some datasets and this one caught my eye. The dataset that I found contains
about 50,000 reviews from IMDB, designated as either positive or negative. So, this was the perfect candiate for my
first binary classification project! I mostly followed a tutorial and heavily relied on AI tools to complete this project, but
I am very glad that I was able to complete this. Now, I'll probably look into creating some sort of computer vision and classification project.
I am curious about the different methods that might be used to determine if an image is similar to another.
I know that for my model, I used TF-IDF tokenization which, to my understanding, determines how important a word is based off how often it occurs and how rare it is.
I wonder if similar processes are used for image classification.
Check out the github here!
Or you can view the deployed version here