Customer reviews sentiment analysis with Python and NLP. Generates a synthetic dataset of positive, neutral, and negative reviews, applies preprocessing (tokenization, stopwords, lemmatization), and builds TF-IDF features. Trains classifiers (Naive Bayes, Logistic Regression, Random Forest) with evaluation, confusion matrix and top features.

Full stack web application for restaurant billing management system

Customer Review Analysis is a prototype open source platform to turn the customer feedbacks in to visualization and extract the trending keywords.

this is my repository for Amazon review helpfulness prediction model

Scraping functions for (1) Amazon customer reviews and (2) product information from best sellers list

This repository includes a web application that is connected to a product recommendation system developed with the comprehensive Amazon Review Data (2018) dataset, consisting of nearly 233.1 million records and occupying approximately 128 gigabytes (GB) of data storage, using MongoDB, PySpark, and Apache Kafka.

Epinions Annotated Reviews Dataset

This repository contains a Python-based sentiment analysis project using Jupyter Notebook to analyze customer reviews. The project leverages TextBlob for sentiment classification, pandas for data manipulation, and Matplotlib/Seaborn for visualizing insights. Key features include: Sentiment Classification,Statistical Analysis

This demo repository demonstrates how to analyze customer reviews with Azure OpenAI Service (AOAI). I leveraged "ASOS Customer Review" from Kaggle to obtain valuable insight from the customer review content.

No description provided.

Big Data Projects

No description provided.

A tool for analyzing Google Play Store reviews

OpenTable Reviews Classification with BERT and Transfer Learning

The project aiming to extract product defects and opinions from customer reviews by using text clustering and sentiment analysis.

Official Fera API ruby SDK gem to make interfacing with your business's reviews easy.

Fera.ai Magento 2 Extension

NLP demos and talks made with Jupyter Notebook and reveal.js

An interactive Tableau dashboard that explores airline customer reviews to uncover passenger satisfaction, sentiment trends, and service quality insights.

Multi-architecture sentiment analysis (LSTM, CNN, FNN) with GloVe embeddings and Bayesian hyperparameter optimization. Comprehensive evaluation of e-commerce review classification with F1-score metrics.

Case Analysis using ML methods to gain insight into customer reviews.

Cutomer reviews analysis and segmentation. Create suggestions for app improvement based on the clustered reviews.

Project: Indian Restaurant Website with HTML CSS JavaScript. Created at https://spectra.codes, which is owned by @Drix10

"ProLyzer" is a system which will guide you about the product you want to buy and also help the manufacturer/sellers to know the public opinion about their product's features.

This project aims to analyze consumer sentiment towards (FMCG) company products by scraping reviews & performing text analysis using Python. By leveraging NLP techniques, such as sentiment analysis, word cloud and topic modelling. The results of this study can inform product development, marketing strategies & overall business decision-making

A real-world NLP project that classifies customer sentiments by product aspects using machine learning and deep learning.

Welcome to the Customer Satisfaction Prediction Project repository! This project analyzes customer satisfaction survey to predict whether a customer is satisfied or dissatisfied based on various features. The goal is to gain insights into factors that contribute to passenger satisfaction and to build a predictive model for future.

Market research and financial analysis of Nykaa with customer review sentiment insights.

Analyzes customer reviews to determine if they're positive or negative using AI

This application manages restaurant reservations, optimizes table allocation (including table merging for larger groups), and handles customer reviews. It evaluates query performance for operations with varying database sizes (20, 1,000, and 5,000 records) both with and without indexing, providing insights into database optimization.