/Sentiment_Analysis

Impact of Feature Extraction on Sentiment Analysis

Primary LanguageJupyter Notebook

Sentiment_Analysis

Implemented feature extraction techniques BOW, N-Gram, TF-IDF and Word2Vec on the restaurant review dataset and did comparative analysis using classification algorithms ( Naive Bayes, Decision Tree, SVM, KNN and Random Forest).
N-Gram(n=2) increased classification accuracy by 7% compared to BOW, TF-IDF and Word2Vec.