abuse-detection

#PAAD: PhoneAccount Abuse Detector for Android 6.0+ devices

Code for the paper "Characterizing and Detecting Hateful Users on Twitter"

Resources and tools for the Tutorial - "Hate speech detection, mitigation and beyond" presented at ICWSM 2021

A curses-style interface for automatic takedown notification based on MISP events.

A profanity checker which, unlike alternatives, uses the Wagner–Fischer algorithm in order to catch variations that you haven't thought of.

Building a dataset of Twitter replies for unsupervised learning / bot-blocking

A simple and lightweight plugin that protects your WordPress against abuse.

A Tensorflow LSTM spam detector utilizing GloVe word embeddings.

Censored word library, Ban abusive words

Author Profiling for Abuse Detection (COLING 2018)

This RocketchatApp validates uploaded images against the Microsoft PhotoDNA cloud service and quarantines those identified as child abuse images (child pornography or CSEM).

API which returns cusswords , can be used to check cusswords in bots etc.

Repository hosting dataset for the Shared Task on Aggression Identification during First Workshop on Trolling, Aggression and Cyberbullying (TRAC - 1) as COLING - 2018. Please visit the workshop website - https://sites.google.com/view/trac1/home - for more details

Google Recaptcha client for kotlin and java

Classifiers that can detect personal attack on a given document

To classify toxic and abusive comments from huge bunch of text.

Chrome extension to automatically block lazy Twitter trolls

serves a notice to the respective abuse/tech-c contacts of banned IPs via fail2ban's log file

Enhance aims to resolve the subject of mental issues among individuals by offering a secure, anonymous environment. Any person can freely discuss his/her problem with other individuals suffering from the same issue with qualified counsellors who can provide solutions to their problems.

FIND: Filters in Discussions

Synchronization between two Wikipedia-based Corpora

Python framework to collect and annotate abusive content from Twitter

A trust based social network for user engagement and protection.

Alert

This work was done as part of Kaggle InClass competition hosted by Sharechat. We had to develop AI solutions for predicting abusive comments posted on the Moj app in 10+ languages given natural language data and user context data.

Repository for the code used in my Master's Thesis: Community-based Abuse Detection: Using Distantly Supervised Data and Biased Word Embeddings

Repository for Studying Abuse Detection (Abusive Language Detection)