▪ Created Naive Bayes based supervised machine learning models to classify hotel reviews into four classes (positive, negative, truthful, or deceptive) by training on Deceptive Opinion Spam Corpus v1.4 and achieved an F1 score of 0.85 on unseen test data.
▪ A naive Bayes classifier to identify hotel reviews as either truthful or deceptive, and either positive or negative. Used the word tokens as features for classification.