AIM - Predict health condition from reviews using Natural Language Processing
Steps Followed : Tokenise the sentences. • Clean reviews : Remove punctuation Remove special characters / numbers Convert to lowercase Lemmatization • Create bag of words model to vectorise • Apply ML algorithms Naive Bayes & Passive Aggressive Classifier • Create TFIDF model to vectorise • Apply ML algorithms Naive Bayes & Passive Aggressive Classifier • Compare different models
The data set can be downloaded from the following URL: https://archive.ics.uci.edu/ml/datasets/Drug+Review+Dataset+%28Drugs.com%29#