📊 Explore advanced machine learning techniques, including NLP, PCA, hyperparameter tuning, and recommendation systems to enhance your data skills.

🎬 Analyze IMDb movie reviews for sentiment using classical and deep learning models, uncovering insights through a comprehensive data science workflow.

Minimal Word2Vec example for training word embeddings and measuring word similarity

Interactive Web App visualizing probabilistic algorithms: Latent Dirichlet Allocation (LDA) for topic modeling, Markov Chains for text generation, and Metropolis-Hastings sampling simulations. Built with Flask & NumPy.

anvay is a Flask-based Bengali text processing and topic modeling tool that uses Latent Dirichlet Allocation (LDA) to extract topics from uploaded text files.

NLP Explorer is a repository dedicated to exploring and applying various Natural Language Processing (NLP) techniques using powerful tools like spaCy, BERT, and Python libraries. This project is a part of my learning journey as an engineering student focused on AI and language understanding.

This Natural Language Processing Projects repository features experiments using Regex, Gensim, spaCy, fastText, Python, and scikit-learn, along with techniques like word embeddings, Word2Vec, BERT, Bag-of-Words, n-grams, and diverse text preprocessing and feature-engineering methods.

This project is about designing a Feedback Analysis by using various NLP Techniques which is commonly used in Recommendations System, and Chatbots.

word vectors for french

Multi-Class Text Classification for products based on their description with Machine Learning algorithms and Neural Networks (MLP, CNN, Distilbert).

Goal: Discover whether modern NLP tools and predictive algorithms can provide insights into ancient text corpora

A project to build a Python-based web scraping and summarization tool that utilizes text paraphrasing.

Маршак против Шекспира: кто победит? Я сделал анализ перевода на Python - результат невероятен! Как код раскроет тайну гения? Почему перевод Маршака — идеален? Доказано математически! https://dzen.ru/video/watch/68da42a8b370df2d6d61e2b7?share_to=link

Sentiment Analysis of IMDB Review Dataset

Topic Modelling for Humans

Word2Vecを使用した日本語単語類似度分析API。Wikipedia出現上位15,000語で学習済み。単語間の類似度計算やベクトル演算（王様 - 男性 + 女性 = 女王）が可能。FastAPIで実装、Railwayでデプロイ済み。。

Sentiment Analysis is a Natural Language Processing (NLP) technique used to identify the emotional tone behind a piece of text — typically classified as positive, negative, or neutral.

A comprehensive set of Jupyter notebooks that take you from NLP fundamentals to advanced techniques. Covers text preprocessing, POS tagging, NER, sentiment analysis (with VADER), text classification, word embeddings, and transformer models like BERT. Built with real-world datasets using NLTK, spaCy, scikit-learn, and Hugging Face Transformers.

Код читает Паустовского: Что LDA рассказывает о персонажах рассказа «Телеграмма». https://dzen.ru/video/watch/68de1cd6b0b0d23bc819834e?share_to=link

This script is written for AI-powered matchmaking system that intelligently pairs users based on their textual responses. It uses Word2Vec embeddings to understand the semantic meaning of responses and cosine similarity to determine how closely two users' responses align.