cntext is a Python library for social science text analysis, offering word frequency, sentiment, word embeddings, and semantic projection to measure constructs like attitudes and psychological states from Chinese text.

Spanish word embeddings computed with different methods and from different corpora

Extracting Skills from resume using Machine Learning

A multi-source supplier risk dataset combining KG scores, semantic similarity, and external disruption signals ideal for supply chain resilience research. Useful for researchers working on supplier risk assessment, multi-objective optimization, or reinforcement learning in dynamic sourcing environments.

Automatic library of congress classification, using word embeddings from book titles and synopses.

The backed for an anime recommender system that combines multiple methods to provide a variety of recommendations to users based on different similarity metrics

Information retrieval course project

Text classification is the task of assigning a set of predefined categories to free text. Text classifiers can be used to organize, structure, and categorize pretty much anything. For example, new articles can be organized by topics, support tickets can be organized by urgency, chat conversations can be organized by language, brand mentions can …

Sentiment Analysis on Loksabha Elections 2019

create the search engine to retrieve the text documents. (the information retrieval course project)

M.Sc. mini project for NLP class (M908)

Bengali word embedding using BengaliWord2Vec from BNLP. A mini project under the mentorship of Prof. Sandipan Ganguly, HIT-K.

An Empirical Evaluation of Word Embedding Models for Subjectivity Analysis Tasks

I created a new technique to do sentiment analysis with 98% probability using multiple techniques combined to from a new method. I made a video on this whole project and show you, how “Next Gen Sentiment” is much better then NLTK, TEXTBLOB or LLMs.

Checkout my adventures into NLP here.

This is final project of Information Retrieval course which is implementation of a search engine

Arabic Word Embedding models SkipGram, and GLoVE are trained over Arabic Wiki data Dump 2018 dataset from scratch using Gensim and GLoVE python libraries. Then the models are evaluated on three NLP tasks and its results are visualized in T-SNE

Automatic library of congress classification, using word embeddings from book titles and synopses.

My work as machine learning intern. Unsupervised Text Clustering and Topic Modeling

Example of how to use word embedding with BlazingText algorithm in Amazon SageMaker on entire contents of wikipedia for a foreign language (Hebrew).