Skip to content

Latest commit

 

History

History
34 lines (26 loc) · 1.73 KB

README.md

File metadata and controls

34 lines (26 loc) · 1.73 KB
Raw

Sentiment-Analysis-on-Womens-Clothing-E-Commerce-Reviews-Dataset

Sentiment analysis training data source

  1. http://ptrckprry.com/course/ssd/data/positive-words.txt
  2. http://ptrckprry.com/course/ssd/data/negative-words.txt

Review data source: Kaggle

Columns in the dataset:

Name Meaning
Clothing ID Unique ID of the product
Age Age of the reviewer
Title Title of the review
Review Text review
Rating Product rating by reviewer
Recommended IND Whether the product is recommended or not by the reviewer
Positive Feedback Count Number of positive feedback on the review
Division Name Name of the division product is in
Department Name Name of the department product is in
Class Name Type of product

Objective:

To do exploratory sentiment analysis and tie it back to product types.

Findings:

Based on the analysis, it is clear that both the reviews for Tops and Dresses contain positive sentiment in abundance to negative sentiment. Anecdotal observation from the plots also suggests that reviews for Dresses tend to be more positive than reviews for Tops.