Recent debate over fake news makes it important to have a method of identifying the validity of headlines. Especially with the nature of the contemporary political atmosphere, satire and real news are increasingly difficult to differentiate.
I Created a K-NN model that analyzes the language in headlines and classifies them as real or satirical news.
I first cleaned a dataset of headlines (from Kaggle) from serious and satirical outlets then analyzed the correlation between language, word count, and title length and whether or not the article is satirical. Used this correlation to classify new headlines.
We used scikit-learn to create a model that predicting the association between California school districts’ financial resource allocations and student academic achievement. The model was run through an optimization algorithm to identify the ideal staff distributions that maximizes achievement
Calculated the time and gas lost by traveling to each location to identify the most efficient location to refill at.