Semantic Analysis
For my Artificial Intelligence class, I built a Sentiment Analysis engine on Mathematica, using a 1/5th test to train ratio. The data was amazon reviews of various products and the goal was to classify the reviews as either positive or negative. The dataset was obtained from Kaggle. The preprocessing of the data included multiple tasks such as converting to lower case, removal of stop words, etc. Followed by the training phase, where we used Neural Nets, Decision trees and Naive Bayes. We compared the results of the various algorithms and produced various visualisations.