Organize and classify files based on their content using NLP
Advanced model of Bm25 is Bm25+, which was implemented and compared with the baseline model (bm25)
🚀 A Job Recommendation Engine built with FastAPI and MongoDB, designed to integrate with a job portal frontend. Uses TF-IDF + Cosine Similarity to recommend jobs to users based on their skills. Exposes a /recommend/{user_id} endpoint that returns personalized job suggestions in real-time.
This project implements a news article retrieval system using dataset of BBC articles. It utilizes FastAPI for the API layer, TF-IDF for term weighting, and Word2Vec and allows users to query the dataset for top-matching articles with similarity scores.
NLP on Women's Clothing Text Reviews
Predict personality types as one of the sixteen categories of Myers Briggs personality types (MBTI) based on the correlation between people's writing styles and their psychological personalities.
Custom Search Engine with web crawling, TF-IDF search ranking, and analytics dashboard
IT5072 - Natural Language Processing Assignment repository for topic identification.
Image gallery - Search based on an images EXIF data
This is a simple implementation of a search system that can read and sort .txt documents by their relevance.
Book recommendation system using NLP ML techniques.
ChatBotFAQs is a lightweight web-based chatbot that answers frequently asked questions using NLP techniques. It uses TF-IDF vectorization and cosine similarity to find the most relevant answer from a predefined set of FAQs.
A beginner-friendly Machine Learning project that classifies SMS messages as Spam or Ham (Not Spam) using Python, Scikit-learn, and TF-IDF vectorization. This project includes text preprocessing, model training, evaluation, and vocabulary visualization using WordClouds.
Disaster Alert Tweet Classifier : ResQTweet is an AI-powered disaster detection and summarization tool that analyzes tweets in real time.
Machine Learning-based E-Commerce Product Recommendation System using Python, TF-IDF Vectorization, Cosine Similarity, and Streamlit.
Explore a comprehensive analysis of Netflix's extensive collection of movies and TV shows, clustering them into distinct categories. This GitHub repository contains all the details, code, and insights into how we've organized and grouped the vast content library into meaningful clusters.
Simple smart email spam classification using machine learning to protect inboxes from unwanted content.
Sistema para recomendación de libros desarrollado en Python con Inteligencia Artigical, utilizando algoritmos como KNN y TD-IDF.
Add a description, image, and links to the td-idf topic page so that developers can more easily learn about it.
To associate your repository with the td-idf topic, visit your repo's landing page and select "manage topics."