Ecommerce product reviews - Pairwise ranking and sentiment analysis

Ecommerce product reviews - Pairwise ranking and sentiment analysis

This project analyzes a dataset containing ecommerce product reviews. The goal is to use machine learning models to perform sentiment analysis on product reviews and rank them based on relevance. Reviews play a key role in product recommendation systems.


Each project comes with 2-5 hours of micro-videos explaining the solution.

Code & Dataset

Get access to 50+ solved projects with iPython notebooks and datasets.

Project Experience

Add project experience to your Linkedin/Github profiles.

What will you learn

Understanding the problem statement and literature survey for review ranking
EDA over textual data
Reviews Text Data Preprocessing - Language Detection, Gibberish Detection, Profanity Detection, and Spelling Correction
How to find gibberish by Markov Chain Concept
Featuring Engineering: Extracting relevance from Reviews Data
Sentiment Analysis: Finding Polarity and Subjectivity from Reviews
Finding text content richness by TF-IDF
EDA with extracted Featured with Target Class
What is Learning to Rank
Pairwise Ranking: In-depth explained, how we used it to rank reviews
Converting Ranking problem to a Classification Problem
Classification Models Spot Checking
Pairwise Ranking reviews with Random Forest Classifier
Evaluation Metrics: Classification Accuracy and Ranking Accuracy
Saving the trained model and developing a Model-Data Pipeline for production use

Project Description

E-Commerce applications provide an added advantage to customers to buy a product with added suggestions in the form of reviews. Obviously, reviews are useful and impactful for customers who are going to buy the products. But these enormous amounts of reviews also create problems for customers as they are not able to segregate useful ones. Regardless, these immense proportions of reviews make an issue for customers as it becomes very difficult to filter informative reviews. This proportional issue has been attempted in this project. The approach that we discuss in detail later ranks reviews based on their relevance with the product and rank down irrelevant reviews.

This work has been done in four phases- data preprocessing/filtering (which includes Language Detection, Gibberish Detection, Profanity Detection), feature extraction, pairwise review ranking, and classification. The outcome will be a list of reviews for a particular product ranking on the basis of relevance using a pairwise ranking approach.

Similar Projects

In this data science project, we will predict the credit card fraud in the transactional dataset using some of the predictive models.

In this project, we are going to talk about Time Series Forecasting to predict the electricity requirement for a particular house using Prophet.

In this machine learning project you will work on creating a robust prediction model of Rossmann's daily sales using store, promotion, and competitor data.

Curriculum For This Mini Project

Business Problem - Product Reviews
Solution - Workflow
Dataset - Exploratory Data Analysis
Data Preprocessing
Feature Engineering - 1
Feature Engineering - 2
EDA after Feature Engineering
What is Pairwise Ranking
Model Training - Spot Checking
Model Ranking Metric
Data pipeline for deployment