Text Classification

A wide range of classifiers are used on three different datasets (spam, toxic and movie). Additionally, NLP techniques for preprocessing text and three word encoders (Tf-Idf, word2vec and GloVe) are used in order to compare results. The next classifiers are implemented:

Logistic Regression
Linear Discriminant Analysis
Quadratic Discriminant Analysis
Random Forest
Multinomial Naive Bayes
Support Vector Machines
Ada Boost
Extreme Gradient Boost
Deep Network (CNN - RNN)

Want to know more?

Click the buttons to get a detailed report of the project or go to the repository on GitHub.