Natural language processing of the Wikipedia text (as far English only) with goals to detect contradictory info, and to create a chat bot providing more accurate answers than ChatGPT.

RaKUn 2.0 - A fast keyword detection algorithm

Legal Insight is an AI-powered system for analyzing legal documents.

Natural Language Processing AI-model driven sentiment analysis system that will automatically process and analyze news articles to gauge market sentiment, and summarizing the news at a weekly level to enhance the accuracy of their stock price predictions and optimize investment strategies.

Python-based web scraping and NLP analysis pipeline for extracting, cleaning, analyzing text, and converting data into structured CSV/Excel formats.

Natural Language Processing (NLP), Large Language Models (LLM)

This repository contains a Streamlit dashboard used to analyze the sentiments of tweets about US airlines. The application displays visualizations and breakdowns of tweet sentiment, time of day, airline choice, and word cloud for specific sentiments.

"A machine learning project to detect fake product reviews using Opinion Mining. It analyzes review text, extracts features, and trains models to classify reviews as genuine or deceptive. The focus is on accuracy and precision to ensure online content authenticity."

VidiNLP is a simple, modern, and fast NLP library built on top of spaCy. It provides easy-to-use functions for common NLP tasks such as tokenization, lemmatization, n-gram extraction, sentiment analysis, text cleaning, keyword extraction, emotion analysis, topic modelling, document similarity.

This repository hosts "From Script to Score: Sentiment Analysis of Film Content", a project exploring how sentiment in movie reviews varies by genre, trigger warnings, ratings, and box office performance. Using data from TMDB, IMDB, Letterboxd, and doesthedogdie.com, and tools like VADER, it uncovers patterns in audience reception and sensitivity.

This project recommends seven tailored asanas based on a user's health conditions. Additionally, our yoga pose estimator detects incorrect postures for improved form.

GAIL INDIA LTD PS: Developed a scalable chatbot leveraging deep learning & NLP to assist employees of large public sector organizations with HR, IT, and organizational queries. Integrated document processing for summarization and information extraction, 2FA for security, and bad language filtering. Achieved <5s response times with open source

This repositiory contains the data and scripts used and produced for my disseration analysis chapter. It contain the discourses of Brazil authorities at the opening of the United Nations Assembly (1985-2024). It also contains initial written scripts in R using some NLP techniques, such as word clouds, inverse frequency, word frequency etc.

Entity Extractor: Leveraging SpaCy for Named Entity Recognition. Extract and classify key entities from text using SpaCy’s powerful NLP models. Simplify text analysis for various applications like document parsing and chatbots.

The project focuses on extracting and structuring key details from resumes such as names, contact information, education, and work experience, into a user-friendly interface for efficient review and management. Additionally, It supports bulk upload of resumes.

Analysis and cluster of thematic trends in Korean linguistic landscape research papers by extracting and canonicalizing keywords from article metadata.

Upload multiple PDFs, ask questions, and get answers instantly using Chat with PDFs.

nlp text mining dashboard to explore current trends and extract most used keywords on software engineering and data science articles. Tech Stack: Django, Python, PostgreSQL, HTML/CSS, JavaScript, Docker, AWS

Resume analyzer to analyze required skills for a job along with buzzword detection and action verb analysis

Data Tagging, Analysis and Insights Generation using Python [NLP, Tokenization]