A minimum-dependency ECMAScript client library and CLI tool for Parler – a "free speech" social network that accepts real money to buy "influence" points to boost organic non-advertising content
Contains code for a voting classifier that is part of an ensemble learning model for tweet classification (which includes an LSTM, a bayesian model and a proximity model) and a system for weighted voting
Hate speech detection from code-mixed Hindi-English tweets using deep learning models. This project reports an increment to the state-of-the-art in hate speech detection for English-Hindi code-mixed tweets. The models result in an improvement of about 12% in F-score over a past work that used statistical classifiers.
Detection and Classification of Hate Speech with the help of Python on twitter texts using Natural Language Processing, Sentiment Analysis and Machine Learning.
An android application created under the framework of the Mandola EU project by the University of Cyprus. Allows the reporting of social media posts containing hate speech to relevant authorities.