PySpark phonetic and string matching algorithms

Implements Rocchio Query Expansion - similar to "related searches:" found at popular search engines but based on relevant documents selected by the end-user

Performs tokenization, stemming, lemmatization, index creation, index compression and ranked retrieval of Cranfield documents

Small code snippets written in Python covering fundamental concepts in NLP used in all major NLP projects.

A Search Engine based on the principle of TF-IDF and comparing documents in a vector space using Cosine Similarity

This project is an end-to-end Fake News Detection System built using Natural Language Processing (NLP) and Machine Learning techniques in Python. It classifies news articles as either Fake or Real.

CS studies - Natural Language Processing project

[BITS M.Tech on Software Systems] Information Retrieval Assignment on Indexing and searching

"# lab-program-1_chu-john_cedrick" Python Implementation of Porter Stemmer

Création d'un moteur de recherche (Parsing de la collection, Index + Index inversé, Ordonnancement, Ranking)

Simple Python Implementation of Stemmer and Lemmatizer

Project in NLP specialization. Bag of words model helps in reading text and predicting the category.

Boolean and proximity retrieval engine over 56 Trump speeches — inverted index, positional index, FastAPI, React

A Search engine that searches for a phrase or word in local text files using stemming and indexing, and returns the matches, in order of relevance, using the tf-idf Algorithm.

A Content-Based Movie Recommendation System built with Python and Scikit-Learn. Leveraging Cosine Similarity on the TMDB 5,000 dataset to suggest films based on metadata. Features real-time poster fetching via TMDB API.