textvectorization

This project employs a deep neural network architecture for the classification of toxic comments, utilizing the Kaggle competition dataset from the Jigsaw Toxic Comment Classification Challenge.

Tex Classification

This project focuses on building a machine learning model to detect fake news articles. The model is trained using a dataset of news articles and utilizes Logistic Regression for classification. The primary goal is to classify news articles as either "real" or "fake" based on their text features such as title and author.

This Repository provides the basic code snippets for all the most widely used ML Algorithms like Supervised, Unsupervised, and Recommender system algorithms.

A content based movie recommender system using cosine similarity

🧠 The project aims to predict the popularity of a movie based on it's overview text. It involves a thorough analysis of a movie dataset, exploring various aspects of data preprocessing, model building, training, and evaluation.

This repository houses a comprehensive Machine Learning project aimed at classifying Yelp reviews using Multinomial Naive Bayes and Natural Language Processing (NLP) techniques.

Content-based Movie Recommender System

Developed a Python-Django server integrated with a machine learning model to provide optimized product recommendations tailored to user preferences, enhances user experience through intelligent, data-driven suggestions.

Built a content-based movie recommendation system using Python and Machine Learning. The system suggests similar movies based on user selection by computing similarity scores using cosine similarity.

Implemented a machine learning model to detect fake news using Natural Language Processing techniques like TF-IDF and stemming. Trained multiple classifiers including Logistic Regression and PassiveAggressiveClassifier for accurate classification. This project showcases practical NLP skills for tackling misinformation in media.

Self-study NLP project comparing sentiment analysis models and applying segment-level inference with mean probability pooling to mitigate training-test data length mismatches