By Shreya Singh
The project classifies the text reviews using the TF-IDF Vectorizer and the prediction is done using support vector machine model using Python language.
The project shows the classification of text reviews using the TF-IDF Vectorizer and the prediction is done using support vector machine model in Python language.
It mainly focuses on the working of TF-IDF Vector which is a machine learning algorithm performing Natural Language Processing (NLP). The TF-IDF vector calculates a score concerning each document, or word The stop words such as 'an', 'is', 'the', are simply words that add no significant value to our system and hence are ignored by the system.
For the project, a consumer review dataset is taken on which preprocessing is done which is then reduced to two columns to reduce the complexity ie. reviews and the score.
After text classification, the model's accuracy and classification report is calculated using the support vector machine model which is about 98% suggesting the quality performance of TF-IDF vectorizer.
Submitted by Shreya Singh (shreyasingh)
Download packets of source code on Coders Packet