Library for fast text representation and extreme classification.

A text analysis application for performing common NLP tasks through a web dashboard interface and an API

Windows Build of fastText, library for text representation and classification.

Modern Türk edebiyatı sınırları içerisinde yer alan dönemleri, eğilimleri, şairleri ve zaman dilimlerini sınıflandıran doğal dil işleme uygulaması.

An autoML for explainable text classification.

Space Model framework that allows for maintaining generalizability, and enhances the performance on the downstream task by utilizing task-specific context attribution. It is an external LLM layer, that improves accuracy in classification task for multiple datasets, such as HateXplain, IMDB movies reviews and more.

Data mining to discover trends in Open Science in Kenya

Implementing text classification algorithms using the 20 newsgroups datasets, with python

python classifier planned with jupyter notebook and uses Flask to service the model of text classification to predict what category an App belongs to

Visualizations of common NLP tasks

Text Analyzer: A web-based tool for performing basic text analysis using HTML, Bootstrap, and JavaScript. Calculate character count, word count, sentence count conversion between uppercase to lowercase & vicevarsa and remove extra lines/spaces effortlessly!

Materials for Fall 2016 Project Mosaic Twitter Text Analytics Workshop

WebApp that Predicts whether provided Text is Spam or Ham

Analysis and Visualizations for COVID-19 Bing search engine queries + Classifier pipeline for predicting country based on search query.

A project to predict the type of webpage from its text.

Indonesia has 19.5 million Twitter users from a total of 500 million global users and continues to grow over time. Twitter users utilize it as a forum for open campaigning by Medan mayoral candidates and their volunteers prompted Netizens to respond. Netizen's response to any tweet is Positive and Negative. Therefore, this research tries to anal…

Spam detection employs machine learning and NLP to identify and filter out unwanted messages. It uses techniques like text classification and feature extraction to distinguish spam from legitimate content, enhancing user security and experience by reducing the impact of malicious or irrelevant messages across digital platforms.

Democratizing Artificial Intelligence

Code repository for https://arxiv.org/abs/2004.01549