text-classification

Tools for automatic frame discovery and labeling based on topic modeling and deep learning, made widely accessible to researchers from non computational backgrounds.

AI Text Detection Web App identifies whether text is AI-generated or human-written. It offers unigram and bigram models, combining Logistic Regression, Naive Bayes, Random Forest, and LightGBM to provide accurate predictions based on text structure and context.

This repository allows Curated News users to see how our open source news headlines text classifier works and operates. It will also allow researchers and academics to vet and verify the strength of our modeling approaches.

Paste any message from Gmail, Slack, or LinkedIn and get a classification, one-line summary, extracted action items, and a suggested reply in seconds. Built with FastAPI, OpenAI, and a vanilla-JS frontend with neon dark theme. Zero-setup productivity tool for inbox overload.

根据文本鉴定 网络小说 还是非网络小说

Machine Learning and NLP-based web application that classifies emails and messages as spam or legitimate using TF-IDF and Logistic Regression, with confidence-based predictions through a Flask web interface.

Machine Learning and NLP classifier to distinguish AI-generated text from human writing.

A modern AI-powered web application for real-time customer review sentiment classification with an interactive dashboard and 97.3% model accuracy using TF-IDF and Logistic Regression.

AI-powered sentiment analysis web application using NLP, TextBlob, NLTK and Scikit-learn.

Spam detector for email/SMS — TF-IDF + 4 NLP classifiers (Logistic Regression ⭐ ~99% accuracy, F1 ~97%) on UCI SMS dataset with Flask UI

SENTINEL — spam detector for SMS and email. TF-IDF + calibrated LinearSVC at 99.4% accuracy, served through a Flask app with a cinematic dark UI.

A simple book recommender system made with NodeJS and mongoDB

Flask web app that classifies customer reviews as positive, negative or neutral using a BERT NLP model.

Project Akhir Mata Kuliah Analisa Big Data untuk melakukan proses prediksi, klasifikasi, dan klasterisasi pada data Tanaman sehingga mendapatkan insight

Fake news classifier — TF-IDF bigrams (50K features) + 4 NLP models (Random Forest ⭐ ~95% accuracy) on 6,300 labelled articles with Flask UI

An AI-powered web application that detects fake news using machine learning. Paste any news article or headline and get an instant REAL / FAKE verdict with a confidence score.

This GitHub repository contains a Chrome extension project designed to filter out tweets containing defamation or slander on Twitter.

This project is a web-based spam detector built with Flask and a Multinomial Naive Bayes classifier from scikit-learn. It classifies messages as "Spam" or "Not Spam" based on a trained dataset. The application features a user-friendly interface that works seamlessly on both mobile and web platforms for real-time spam prediction.