Dataset The dataset that is from Nick Brooks' Kaggle a Women’s Clothing E-Commerce site, which has reviews written by customers.In addition, the dataset has been anonymized, and references to the company in the review text and body have been replaced with “retailer”. In this project, I would like to classify each review whether it recommends the reviewed product or not, so the Recommended IND field will be the outcome. The other supportive features offer a great environment to parse out the text through its multiple dimensions.
This dataset includes 23486 rows and 10 feature variables
The data analyst team at an e-commerce company selling women clothing wants to know what customers like and dislike about our clothes and predict what kinds of clothes our customer would like to recommend based on the analyzing the customer reviews on an e-commerce clothing site.
Target variable: Recommended IND (0: Not recommended , 1: Recommended)
Sentiment Analysis: Reviews- Positive, Negative , Neutral