Model that predicts the probability of a Twitter user being anti-vaccination.

Overview
<style>body {text-align: justify}</style>

AVAXTAR: Anti-VAXx Tweet AnalyzeR

AVAXTAR is a python package to identify anti-vaccine users on twitter. The model outputs complimentary probabilities for [not anti-vaccine, anti-vaccine]. AVAXTAR was trained on 100GB of autolabeled twitter data.

The model supports both Twitter API v1 and v2. To predict with v1, the user needs its consumer key, consumer secret, access token and access secret. The v2 requires only a bearer token, but it can only predict based on user id, not on screen name. Predicting from the v2 api using screen name is only possible if v1 keys are passed to the model.

The methodology behind the package is described in full at {placeholder}

Citation

To cite this paper, please use: {placeholder}

Installation

Attention: this package relies on a pre-trained embedding model from sent2vec, with a size of 5 GB. The model will be automatically downloaded when the package is first instanced on a python script, and will then be saved on the package directory for future usage.

  1. Clone this repo:
git clone https://github.com/Matheus-Schmitz/avaxtar.git
  1. Go to the repo's root:
cd avaxtar/
  1. Install with pip:
pip install .

Usage Example

For prediction, use:

model.predict_from_userid_api_v1(userid)

and:

model.predict_from_userid_api_v2(userid)

For example:

from avaxtar import Avaxtar

consumer_key = ''
consumer_secret = ''
access_token = ''
access_secret = ''
bearer_token = ''


if __name__ == "__main__":

	# Get the userid
	userid = ''

	# Predict
	model = Avaxtar.AvaxModel(consumer_key, consumer_secret, access_token, access_secret, bearer_token)
	pred_proba = model.predict_from_userid_api_v1(userid)

	# Results
	print(f'User: {userid}')
	print(f'Class Probabilities: {pred_proba}')

Package Details

The AVAXTAR classifier is trained on a comprehensive labeled dataset that contains historical tweets of approximately 130K Twitter accounts. Each account from the dataset was assigned one out of two labels: positive for the accounts that actively spread anti-vaccination narrative \~70K and negative for the accounts that do not spread anti vaccination narrative \~60K.

Collecting positive samples: Positive samples are gathered through a snowball method to identify a set of hashtags and keywords associated with the anti-vaccination movement, and then queried the Twitter API and collected the historical tweets of accounts that used any of the identified keywords.

Collecting negative samples: To collect the negative samples, we first performed a mirror approach the positive samples and queried the Twitter API to get historical tweets of accounts that do not use any of the predefined keywords and hashtags. We then enlarge the number of negative samples, by gathering the tweets from accounts that are likely proponents of the vaccination. We identify the pro-ponents of the vaccines in the following way: First, we identify the set of twenty most prominent doctors and health experts active on Twitter. Then collected the covid-related Lists those health experts made on Twitter. From those lists, we collected approximately one thousand Twitter handles of prominent experts and doctors who tweet about the coronavirus and the pandemic. In the next step, we go through their latest 200 tweets and collected the Twitter handles of users who retweeted their tweets. That became our pool of pro-vaccine users. Finally, we collected the historical tweets of users from the pro-vaccine pool.

After model training, we identify the optimal classification threshold to be used, based on maximizing F1 score on the validation set. We find that a threshold of 0.5938 results in the best F1 Score, and thus recommend the usage of that threshold instead of the default threshold of 0.5. Using the optimized threshold, the resulting modelwas then evaluated on a test set of users, achieving the reasonable scores, as shown in the table below.

Metric Negative Class Positive Class
Accuracy 0.8680 0.8680
ROC-AUC 0.9270 0.9270
PRC-AUC 0.8427 0.9677
Precision 0.8675 0.8675
Recall 0.8680 0.8680
F1 0.8677 0.8678
Official Implementation of "Learning Disentangled Behavior Embeddings"

DBE: Disentangled-Behavior-Embedding Official implementation of Learning Disentangled Behavior Embeddings (NeurIPS 2021). Environment requirement The

Mishne Lab 12 Sep 28, 2022
Files for a tutorial to train SegNet for road scenes using the CamVid dataset

SegNet and Bayesian SegNet Tutorial This repository contains all the files for you to complete the 'Getting Started with SegNet' and the 'Bayesian Seg

Alex Kendall 800 Dec 31, 2022
Simple Pixelbot for Diablo 2 Resurrected written in python and opencv.

Simple Pixelbot for Diablo 2 Resurrected written in python and opencv. Obviously only use it in offline mode as it is against the TOS of Blizzard to use it in online mode!

468 Jan 03, 2023
[CVPR 2021] Exemplar-Based Open-Set Panoptic Segmentation Network (EOPSN)

EOPSN: Exemplar-Based Open-Set Panoptic Segmentation Network (CVPR 2021) PyTorch implementation for EOPSN. We propose open-set panoptic segmentation t

Jaedong Hwang 49 Dec 30, 2022
Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks

Adversarially-Robust-Periphery Code + Data from the paper "Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks" by A

Anne Harrington 2 Feb 07, 2022
This project provides a stock market environment using OpenGym with Deep Q-learning and Policy Gradient.

Stock Trading Market OpenAI Gym Environment with Deep Reinforcement Learning using Keras Overview This project provides a general environment for stoc

Kim, Ki Hyun 769 Dec 25, 2022
A pre-trained model with multi-exit transformer architecture.

ElasticBERT This repository contains finetuning code and checkpoints for ElasticBERT. Towards Efficient NLP: A Standard Evaluation and A Strong Baseli

fastNLP 48 Dec 14, 2022
Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集

English | 简体中文 Latest News 2021.10.25 Paper "Docking-based Virtual Screening with Multi-Task Learning" is accepted by BIBM 2021. 2021.07.29 PaddleHeli

633 Jan 04, 2023
Safe Local Motion Planning with Self-Supervised Freespace Forecasting, CVPR 2021

Safe Local Motion Planning with Self-Supervised Freespace Forecasting By Peiyun Hu, Aaron Huang, John Dolan, David Held, and Deva Ramanan Citing us Yo

Peiyun Hu 90 Dec 01, 2022
PyTorch implementation of DeepUME: Learning the Universal Manifold Embedding for Robust Point Cloud Registration (BMVC 2021)

DeepUME: Learning the Universal Manifold Embedding for Robust Point Cloud Registration [video] [paper] [supplementary] [data] [thesis] Introduction De

Natalie Lang 10 Dec 14, 2022
The fundamental package for scientific computing with Python.

NumPy is the fundamental package needed for scientific computing with Python. Website: https://www.numpy.org Documentation: https://numpy.org/doc Mail

NumPy 22.4k Jan 09, 2023
Space-invaders - Simple Game created using Python & PyGame, as my Beginner Python Project

Space Invaders This is a simple SPACE INVADER game create using PYGAME whihc hav

Gaurav Pandey 2 Jan 08, 2022
Collection of tasks for fast prototyping, baselining, finetuning and solving problems with deep learning.

Collection of tasks for fast prototyping, baselining, finetuning and solving problems with deep learning Installation

Pytorch Lightning 1.6k Jan 08, 2023
Code for paper "Vocabulary Learning via Optimal Transport for Neural Machine Translation"

**Codebase and data are uploaded in progress. ** VOLT(-py) is a vocabulary learning codebase that allows researchers and developers to automaticaly ge

416 Jan 09, 2023
Proximal Backpropagation - a neural network training algorithm that takes implicit instead of explicit gradient steps

Proximal Backpropagation Proximal Backpropagation (ProxProp) is a neural network training algorithm that takes implicit instead of explicit gradient s

Thomas Frerix 40 Dec 17, 2022
Non-Attentive-Tacotron - This is Pytorch Implementation of Google's Non-attentive Tacotron.

Non-attentive Tacotron - PyTorch Implementation This is Pytorch Implementation of Google's Non-attentive Tacotron, text-to-speech system. There is som

Jounghee Kim 46 Dec 19, 2022
🔊 Audio and fastai v2

Fastaudio An audio module for fastai v2. We want to help you build audio machine learning applications while minimizing the need for audio domain expe

152 Dec 28, 2022
Vit-ImageClassification - Pytorch ViT for Image classification on the CIFAR10 dataset

Vit-ImageClassification Introduction This project uses ViT to perform image clas

Kaicheng Yang 4 Jun 01, 2022
Pytorch implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion"

MOSNet pytorch implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion" https://arxiv.org/abs/1904.08352 Dependency L

9 Nov 18, 2022
Minimisation of a negative log likelihood fit to extract the lifetime of the D^0 meson (MNLL2ELDM)

Minimisation of a negative log likelihood fit to extract the lifetime of the D^0 meson (MNLL2ELDM) Introduction The average lifetime of the $D^{0}$ me

Son Gyo Jung 1 Dec 17, 2021